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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     embrace
    -0.08
     district
    -0.07
    瞌
    -0.07
    戽
    -0.07
    Managing
    -0.07
    칫
    -0.07
    Fail
    -0.06
    .Scroll
    -0.06
    することが
    -0.06
    Uid
    -0.06
    POSITIVE LOGITS
    objet
    0.08
    .fb
    0.08
    阜阳
    0.07
    ɘ
    0.07
    undos
    0.07
     örnek
    0.07
    _utilities
    0.07
    ≒
    0.07
    postgres
    0.06
    빚
    0.06
    Act Density 0.045%

    No Known Activations