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

    Neuronpedia

    INDEX
    Explanations

    200, 201

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tran
    -0.07
    ependency
    -0.07
    пор
    -0.06
     aver
    -0.06
     apt
    -0.06
    zza
    -0.06
    рот
    -0.06
     Sensors
    -0.06
     FIR
    -0.06
    rant
    -0.06
    POSITIVE LOGITS
    .toastr
    0.07
    _TW
    0.07
    До
    0.06
    였
    0.06
    خدم
    0.06
     جن
    0.06
    ~↵
    0.06
    252
    0.06
     малень
    0.06
    过
    0.06
    Act Density 0.001%

    No Known Activations