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

    Neuronpedia

    INDEX
    Explanations

    indented bullet points and symbols used in math equations or computer code

    oai_token-act-pair · gemini-2.0-flash

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     externi
    -0.63
    __(/*!
    -0.60
    :✨
    -0.60
     nakalista
    -0.59
    Tembelea
    -0.55
    }}$\\
    -0.51
    Diwedd
    -0.50
    GEBURTSDATUM
    -0.50
    ßten
    -0.50
     ExecuteAsync
    -0.49
    POSITIVE LOGITS
    脚注の使い方
    0.77
    StructEnd
    0.71
    FunctionFlags
    0.68
     estekak
    0.63
    RegistryLite
    0.60
     buoy
    0.59
    NOPQRST
    0.58
     thighs
    0.58
    addWidget
    0.57
    LayoutStyle
    0.56
    Act Density 1.351%

    No Known Activations