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

    Neuronpedia

    INDEX
    Explanations

    publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Anc
    -0.07
     cryptoc
    -0.07
    先
    -0.07
     않았
    -0.06
     �
    -0.06
     し
    -0.06
     способом
    -0.06
    OGRAPH
    -0.06
     پاد
    -0.06
    .GetAsync
    -0.06
    POSITIVE LOGITS
    _tile
    0.07
    ermal
    0.06
    Bitte
    0.06
    (;
    0.06
    mí
    0.06
    essages
    0.06
     debugging
    0.06
    .Evaluate
    0.06
    .dsl
    0.06
    -aged
    0.06
    Act Density 0.012%

    No Known Activations