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

    Neuronpedia

    INDEX
    Explanations

    Ordinal suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    embourg
    -0.07
    cors
    -0.06
    adders
    -0.06
     Replica
    -0.06
    дами
    -0.06
     nabízí
    -0.06
     uom
    -0.06
    _LOC
    -0.06
    rms
    -0.06
     argued
    -0.06
    POSITIVE LOGITS
     Fighter
    0.08
    寒
    0.07
    _pdata
    0.07
     "*
    0.07
     �
    0.06
     ه
    0.06
    .rot
    0.06
    02
    0.06
     dostan
    0.06
     `[
    0.06
    Act Density 0.003%

    No Known Activations