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
    zing
    -0.06
     '<
    -0.06
    こう
    -0.06
     phiếu
    -0.06
    leness
    -0.06
     Law
    -0.06
     skill
    -0.06
    tim
    -0.06
    India
    -0.06
    .units
    -0.06
    POSITIVE LOGITS
     herk
    0.07
     &↵
    0.07
    _dyn
    0.07
    /disc
    0.06
    озна
    0.06
    controls
    0.06
    town
    0.06
    ální
    0.06
     Sole
    0.06
    ประส
    0.06
    Act Density 0.000%

    No Known Activations