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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tv
    -0.07
    &t
    -0.07
     tennis
    -0.07
     orgas
    -0.06
    ќ
    -0.06
    .dense
    -0.06
     عن
    -0.06
    /pub
    -0.06
    _Status
    -0.06
     NSError
    -0.06
    POSITIVE LOGITS
    وزی
    0.06
    lassen
    0.06
    rotate
    0.06
     witches
    0.05
     Пер
    0.05
     zajist
    0.05
    쓰
    0.05
    sınız
    0.05
     temporarily
    0.05
    vn
    0.05
    Act Density 0.100%

    No Known Activations