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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    435
    -0.07
     permite
    -0.06
    etroit
    -0.06
    =title
    -0.06
     Aw
    -0.06
     Reserve
    -0.06
     Hop
    -0.06
    876
    -0.06
    enu
    -0.06
    blers
    -0.06
    POSITIVE LOGITS
    “Our
    0.07
    Registrar
    0.07
     карт
    0.07
    <uint
    0.07
    *m
    0.07
    "Our
    0.06
    (input
    0.06
    /(?
    0.06
     dictionaryWith
    0.06
     naval
    0.06
    Act Density 0.005%

    No Known Activations