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

    Neuronpedia

    INDEX
    Explanations

    code, names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.59
    SourceChecksum
    -0.53
     AssemblyCulture
    -0.50
    yntaxException
    -0.50
    vably
    -0.49
     CanadaChoose
    -0.47
     referenties
    -0.46
     BrowserModule
    -0.45
    hibli
    -0.45
    codegen
    -0.45
    POSITIVE LOGITS
     FetchType
    0.64
     endwhile
    0.59
     forKey
    0.58
     gogh
    0.58
    </tfoot>
    0.57
    PostMapping
    0.57
    ButtonModule
    0.54
     metálico
    0.54
    CppMethod
    0.53
    פרי
    0.52
    Act Density 0.003%

    No Known Activations