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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and names

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.69
    )，
    -0.54
    )。
    -0.52
    )：
    -0.50
    ”，
    -0.50
    ”？
    -0.50
    )…
    -0.50
    )’
    -0.49
    ”。
    -0.49
    )”
    -0.48
    POSITIVE LOGITS
     समीक्षाओं
    0.68
    ftagPool
    0.65
    DockStyle
    0.63
     useDispatch
    0.60
     BoxFit
    0.59
     SqlCommand
    0.59
    LookAnd
    0.59
    IndentedString
    0.58
    CopyWith
    0.57
    ValueStyle
    0.56
    Act Density 2.806%

    No Known Activations