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

    Neuronpedia

    INDEX
    Explanations

    Programming functions/methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quet
    -0.08
     ignorance
    -0.07
    期望
    -0.07
     telecom
    -0.07
    nom
    -0.07
     unimagin
    -0.07
     midst
    -0.07
     Thương
    -0.06
     nombre
    -0.06
    usting
    -0.06
    POSITIVE LOGITS
    (always
    0.07
    Eta
    0.07
     midi
    0.07
    pgsql
    0.07
    .Mutable
    0.07
    _mutex
    0.07
    といって
    0.07
    _yaw
    0.07
    _BYTES
    0.07
    🐗
    0.06
    Act Density 0.055%

    No Known Activations