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

    Neuronpedia

    INDEX
    Explanations

    ().

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Арх
    -0.07
    ”的
    -0.07
     जम
    -0.07
    واهد
    -0.06
     raid
    -0.06
     Enum
    -0.06
     Giá
    -0.06
     certain
    -0.06
    .Header
    -0.06
    sworth
    -0.06
    POSITIVE LOGITS
    .reduce
    0.07
    šní
    0.07
     Denied
    0.06
     Rudy
    0.06
    밍
    0.06
    _MEDIA
    0.06
    ικές
    0.06
     offense
    0.06
    looking
    0.06
    iforn
    0.06
    Act Density 0.000%

    No Known Activations