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

    Neuronpedia

    INDEX
    Explanations

    typescript, abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ts
    -1.11
    ted
    -0.97
    TS
    -0.66
    KommentareTeilen
    -0.56
    TED
    -0.55
    levance
    -0.54
    IDATE
    -0.54
    ed
    -0.53
    Address
    -0.53
     AssemblyVersion
    -0.53
    POSITIVE LOGITS
     насеље
    0.69
     the
    0.60
    iprot
    0.60
    Література
    0.60
     Roskov
    0.58
    mgang
    0.57
    erv
    0.56
    textTheme
    0.56
     Италијани
    0.56
    numerusform
    0.55
    Act Density 0.042%

    No Known Activations