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

    Neuronpedia

    INDEX
    Explanations

    attorney

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slog
    -0.07
     Papa
    -0.06
    scri
    -0.06
     Ning
    -0.06
    !↵↵↵↵
    -0.06
     pool
    -0.06
     rang
    -0.06
     boat
    -0.06
     tandem
    -0.06
    _);
↵
    -0.06
    POSITIVE LOGITS
    止
    0.07
     تصمیم
    0.07
     включа
    0.07
    cus
    0.07
     حاضر
    0.06
     inflater
    0.06
    θούν
    0.06
    ело
    0.06
    rm
    0.06
    CppType
    0.06
    Act Density 0.002%

    No Known Activations