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

    Neuronpedia

    INDEX
    Explanations

    program code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.52
     VIDEOTAPE
    -0.50
    complexContent
    -0.46
    XMLSchema
    -0.45
    +:+
    -0.45
    发表于
    -0.43
     odkazy
    -0.42
     상세
    -0.42
    ########.
    -0.42
     Walkover
    -0.42
    POSITIVE LOGITS
    //
    0.31
    BindView
    0.26
    [toxicity=0]
    0.25
     Jefus
    0.24
    <h1>
    0.24
    konomi
    0.23
    anueva
    0.23
     بيها
    0.23
     Nacionales
    0.23
    <h2>
    0.22
    Act Density 5.334%

    No Known Activations