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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific words related to verification, confirmation, and identity

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

    Capitalized first word of a line

    np_acts-logits-general · gemini-2.0-flash

    Pri, Bij

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueGeneration
    -0.57
    ReusableCell
    -0.54
    principalTable
    -0.53
    /**
    -0.53
    XmlAccessType
    -0.53
    RegisterType
    -0.53
    twimg
    -0.51
    endpush
    -0.50
     كومونز
    -0.49
     Diarsipkan
    -0.49
    POSITIVE LOGITS
     linkovi
    0.71
    titudes
    0.59
     least
    0.56
     Bigelow
    0.54
     Roskov
    0.53
    +',
    0.53
     ECL
    0.53
     ddelweddau
    0.52
    tvguidetime
    0.52
    jarati
    0.52
    Act Density 0.021%

    No Known Activations