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

    Neuronpedia

    INDEX
    Explanations

    workbook

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyVersion
    -0.74
    IntoConstraints
    -0.69
     /\.(
    -0.68
     ArrayAdapter
    -0.65
    windowFixed
    -0.65
    ArrayAdapter
    -0.64
     ruled
    -0.63
    oneofs
    -0.63
    webElement
    -0.61
    Pinus
    -0.60
    POSITIVE LOGITS
     Guzmán
    0.49
     Mawr
    0.49
    íše
    0.48
     Lighter
    0.47
    igation
    0.47
    hg
    0.46
     stabilité
    0.46
    oan
    0.46
    getragen
    0.46
     Effectively
    0.46
    Act Density 0.190%

    No Known Activations