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

    Neuronpedia

    INDEX
    Explanations

    names of people, especially those involved in legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.54
    ărul
    -0.50
     Selva
    -0.47
    zkod
    -0.46
    masan
    -0.45
     Schilder
    -0.44
     Crock
    -0.43
     schle
    -0.43
     Salad
    -0.42
     informée
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.72
    setVerticalGroup
    0.63
    SequentialGroup
    0.61
    nonatomic
    0.59
    providedIn
    0.57
     CURIAM
    0.56
    RenderAtEndOf
    0.55
     InputDecoration
    0.54
    ActionTypes
    0.54
    ---|---|
    0.54
    Act Density 3.112%

    No Known Activations