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

    Neuronpedia

    INDEX
    Explanations

    ceiling/limit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sanat
    -0.07
    628
    -0.06
     Ariel
    -0.06
     harmless
    -0.06
    .market
    -0.06
     Plato
    -0.06
     nearer
    -0.06
    (plan
    -0.06
     προ
    -0.06
     ATTR
    -0.06
    POSITIVE LOGITS
    /schema
    0.09
    .AttributeSet
    0.07
     opráv
    0.07
    Lux
    0.07
    _gc
    0.07
     ',',
    0.06
    .useState
    0.06
    ']],
    0.06
    .EventArgs
    0.06
    .AddParameter
    0.06
    Act Density 0.001%

    No Known Activations