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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    #######
    -0.07
     cryptographic
    -0.07
     Predictor
    -0.06
     krit
    -0.06
    _UNKNOWN
    -0.06
     Teil
    -0.06
     smarter
    -0.06
     �
    -0.06
     понять
    -0.06
    .hstack
    -0.06
    POSITIVE LOGITS
    )){↵↵
    0.07
    adians
    0.07
     مشکلات
    0.07
    ceipt
    0.06
    ров
    0.06
    eros
    0.06
    \":{\"
    0.06
     childish
    0.06
    -transition
    0.06
    sut
    0.06
    Act Density 0.009%

    No Known Activations