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

    Neuronpedia

    INDEX
    Explanations

    a mix of direction-related terms and xml path data

    oai_token-act-pair · gemini-2.0-flash

    L

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.63
    styleType
    -0.62
    IsMutable
    -0.53
    EndContext
    -0.53
    enterOuterAlt
    -0.52
    PRWEB
    -0.51
    UnusedPrivate
    -0.51
    KURZBESCHREIBUNG
    -0.51
    UnsafeEnabled
    -0.50
     ✭✭
    -0.49
    POSITIVE LOGITS
     mại
    0.67
     ویکی‌پدیا
    0.67
     onCreateView
    0.65
     umani
    0.65
    Above
    0.59
    raria
    0.58
     fished
    0.57
     שוליים
    0.56
    новништво
    0.56
    rophobic
    0.55
    Act Density 1.978%

    No Known Activations