Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the word "при" and its variations, likely indicating a focus on the Russian language or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text/code snippets related to phone numbers or codes

    np_acts-logits-general · gemini-2.0-flash

    Primates, primarily, ved første, sagittal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.71
    RegisterType
    -0.67
    principalTable
    -0.65
    endpush
    -0.62
    ValueGeneration
    -0.59
     ویکی‌پدیا
    -0.57
    twimg
    -0.55
    ContentAlignment
    -0.55
    //
    -0.53
     كومونز
    -0.53
    POSITIVE LOGITS
     linkovi
    0.63
     least
    0.57
    titudes
    0.55
    +',
    0.54
     ddelweddau
    0.52
     Correspond
    0.52
     biv
    0.51
     المعيارى
    0.50
    Tink
    0.49
    бл
    0.48
    Act Density 0.010%

    No Known Activations