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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    74
    -0.07
     지정
    -0.07
    Tpl
    -0.07
     personally
    -0.07
    297
    -0.07
     addresses
    -0.07
    +".
    -0.07
     дов
    -0.06
    :↵↵↵↵
    -0.06
    руют
    -0.06
    POSITIVE LOGITS
    (Product
    0.06
     Already
    0.06
    /licenses
    0.06
     Họ
    0.06
     microbi
    0.06
    _pll
    0.06
    _slices
    0.06
    (color
    0.06
     twitter
    0.06
    .depart
    0.06
    Act Density 0.000%

    No Known Activations