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

    Neuronpedia

    INDEX
    Explanations

    domain suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pot
    -0.07
    ↵		
↵
    -0.07
     -------------------------------------------------------------------------↵
    -0.07
    queries
    -0.07
     real
    -0.07
     č
    -0.06
     waste
    -0.06
     drink
    -0.06
     Week
    -0.06
     thereof
    -0.06
    POSITIVE LOGITS
    .PageSize
    0.06
     телеф
    0.06
    .SK
    0.06
     Rid
    0.06
    _ALWAYS
    0.06
    _progress
    0.06
    OVÁ
    0.06
    手机号
    0.06
    .Clamp
    0.06
     підстав
    0.06
    Act Density 0.002%

    No Known Activations