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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getWidth
    -0.06
    *e
    -0.06
    -0.06
    .Sh
    -0.06
    (verbose
    -0.06
    Development
    -0.06
    ?”
    -0.06
    builtin
    -0.06
    /payment
    -0.06
    くの
    -0.06
    POSITIVE LOGITS
     happ
    0.07
    ię
    0.07
    .cap
    0.07
     перек
    0.06
    _Impl
    0.06
     Grinding
    0.06
    521
    0.06
     Gi�
    0.06
     hol
    0.06
    _NOTICE
    0.06
    Act Density 0.003%

    No Known Activations