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

    Neuronpedia

    INDEX
    Explanations

    numerical values or phrases referring to quantities and statistics

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

    Numbers indicating quantities or time

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by years or percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.81
    IntoConstraints
    -0.79
    AxisAlignment
    -0.77
    setVerticalGroup
    -0.74
    GIVEREF
    -0.73
     WaitForSeconds
    -0.72
    withIdentifier
    -0.72
    شهاد
    -0.72
    addGap
    -0.69
    ConstraintMaker
    -0.69
    POSITIVE LOGITS
    two
    0.80
    one
    0.80
    something
    0.75
    five
    0.74
     one
    0.72
    six
    0.68
    nine
    0.68
    seven
    0.64
     two
    0.64
    four
    0.63
    Act Density 0.068%

    No Known Activations