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

    Neuronpedia

    INDEX
    Explanations

    the, in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _d
    -0.06
    03
    -0.06
     Truy
    -0.06
     Д
    -0.06
    _R
    -0.06
    <U
    -0.06
    .Collectors
    -0.06
    IGINAL
    -0.06
    870
    -0.06
    ;d
    -0.06
    POSITIVE LOGITS
    谋
    0.07
     pagamento
    0.07
    Str
    0.06
    lobby
    0.06
    Birth
    0.06
    lys
    0.06
     Lobby
    0.06
    Facebook
    0.06
    &A
    0.06
    .ham
    0.06
    Act Density 0.041%

    No Known Activations