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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shop
    -0.08
    に
    -0.07
    quarters
    -0.07
    .scal
    -0.07
    d
    -0.07
     share
    -0.07
    dl
    -0.07
    etin
    -0.06
    ede
    -0.06
     Boat
    -0.06
    POSITIVE LOGITS
    ξης
    0.06
    fill
    0.06
    .uf
    0.06
    Alg
    0.06
    μων
    0.06
    ۀ
    0.06
    URING
    0.05
    NK
    0.05
    atura
    0.05
    _xlabel
    0.05
    Act Density 0.053%

    No Known Activations