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

    Neuronpedia

    INDEX
    Explanations

    AP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ąd
    -0.07
    keepers
    -0.06
    İM
    -0.06
    phil
    -0.06
    Along
    -0.06
    ül
    -0.06
    Matcher
    -0.06
    (groups
    -0.06
     Rodgers
    -0.06
    -with
    -0.06
    POSITIVE LOGITS
    /inet
    0.07
    ycl
    0.07
    _Base
    0.06
    .Box
    0.06
    hma
    0.06
    _BASIC
    0.06
     Mirror
    0.06
    ivityManager
    0.06
    _destroy
    0.06
     다시
    0.06
    Act Density 0.001%

    No Known Activations