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

    Neuronpedia

    INDEX
    Explanations

    rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estekak
    -0.64
    DoubleQuotes
    -0.52
    sen
    -0.52
    互联网档案馆
    -0.47
    jsii
    -0.46
     gero
    -0.45
     Herod
    -0.45
    ográficas
    -0.43
    Superview
    -0.43
    lami
    -0.43
    POSITIVE LOGITS
     rundt
    0.75
     around
    0.68
    SizeMode
    0.67
    around
    0.61
     вокруг
    0.59
     Around
    0.59
    matchCondition
    0.59
    łgor
    0.58
    Around
    0.58
     autour
    0.58
    Act Density 0.009%

    No Known Activations