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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement and support in discussions

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

    Agreement or acknowledgement in online posts

    np_acts-logits-general · gemini-2.0-flash

    referencing comments or posters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     архивлан
    -0.70
    AndroidJUnit
    -0.69
    writeFieldEnd
    -0.67
    InputBorder
    -0.65
    dafx
    -0.63
    RectangleBorder
    -0.63
    ReusableCell
    -0.63
    хьтан
    -0.62
    noinspection
    -0.60
    ViewFeatures
    -0.60
    POSITIVE LOGITS
     mentioned
    0.96
     suggestion
    0.88
     OP
    0.86
     above
    0.84
    mentioned
    0.83
     posted
    0.82
     comments
    0.81
     mention
    0.79
     posting
    0.78
     commenter
    0.77
    Act Density 0.433%

    No Known Activations