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

    Neuronpedia

    INDEX
    Explanations

    the word "scale" with related words.

    oai_token-act-pair · gemini-2.0-flash

    scale

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.91
    хьтан
    -0.87
    SharedDtor
    -0.75
     '{@
    -0.75
     Réponses
    -0.74
     Efq
    -0.71
    WebVitals
    -0.71
     kasarigan
    -0.71
     nahilalakip
    -0.70
    BagConstraints
    -0.69
    POSITIVE LOGITS
    umani
    0.46
    webElement
    0.42
     }).
    0.42
    meli
    0.41
     be
    0.41
    baye
    0.41
    hagen
    0.40
    laf
    0.38
    ])).
    0.38
    UNUSED
    0.38
    Act Density 8.974%

    No Known Activations