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

    Neuronpedia

    INDEX
    Explanations

    nouns representing a variety of disparate concepts

    oai_token-act-pair · gemini-2.0-flash

    shoes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.89
    ConstraintMaker
    -0.84
    ArgsConstructor
    -0.74
     InputDecoration
    -0.67
     ivelany
    -0.60
     Administrativna
    -0.59
    AutoresizingMask
    -0.57
     tänka
    -0.57
    AddHtmlAttribute
    -0.56
    seamnă
    -0.55
    POSITIVE LOGITS
    <bos>
    0.72
    __':
    0.67
    __":
    0.55
    __':
    0.54
    delu
    0.52
    riss
    0.52
    riva
    0.50
    kiat
    0.50
    bazel
    0.50
    creva
    0.49
    Act Density 0.898%

    No Known Activations