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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and expressions of uncertainty

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

    followed by a comma

    np_acts-logits-general · gemini-2.0-flash

    question or possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Хочу
    -0.56
     ayrıca
    -0.54
    cèse
    -0.52
    OkHttpClient
    -0.52
    DoubleQuotes
    -0.51
    tvguidetime
    -0.50
    همچنین
    -0.49
     jenner
    -0.49
     extensively
    -0.49
    Filmo
    -0.48
    POSITIVE LOGITS
     the
    0.88
     unknownFields
    0.82
     things
    0.77
     neither
    0.69
     '{@
    0.68
     momentum
    0.64
    FTFY
    0.64
     nothing
    0.62
    millimeters
    0.60
     those
    0.59
    Act Density 0.398%

    No Known Activations