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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -builder
    -0.06
     morally
    -0.06
     compra
    -0.06
    وير
    -0.06
    /m
    -0.06
     shaft
    -0.06
    .activities
    -0.06
    shaft
    -0.06
     Weird
    -0.06
    ٨
    -0.06
    POSITIVE LOGITS
    (reader
    0.07
     Çalış
    0.07
     YEARS
    0.07
    _POSTFIELDS
    0.06
     لق
    0.06
     BEGIN
    0.06
    iscrimination
    0.06
    portion
    0.06
    ?action
    0.06
     scouting
    0.06
    Act Density 0.001%

    No Known Activations