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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Params
    -0.08
     lure
    -0.07
    _CITY
    -0.07
     CreateTable
    -0.07
     createSelector
    -0.07
    curacy
    -0.07
    Tor
    -0.07
    .mail
    -0.07
     karde
    -0.07
     gamble
    -0.07
    POSITIVE LOGITS
    請
    0.07
    -priced
    0.07
    发票
    0.07
     EX
    0.07
    ート
    0.07
    Metadata
    0.06
    离退休
    0.06
     applied
    0.06
    _document
    0.06
    _velocity
    0.06
    Act Density 0.005%

    No Known Activations