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

    Neuronpedia

    INDEX
    Explanations

    elements related to function signatures and variable declarations in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens before constructor calls and expressions

    np_acts-logits-general · gemini-2.0-flash

    code expressions, assignments, properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erate
    -0.52
    XmlEnum
    -0.48
    ystema
    -0.48
     histor
    -0.48
     Thi
    -0.47
    iolo
    -0.47
     success
    -0.47
     Buk
    -0.47
    Ārējās
    -0.46
     Dun
    -0.46
    POSITIVE LOGITS
    省市镇
    0.67
     religieuses
    0.63
    RenderAtEndOf
    0.63
     vertes
    0.62
     שוליים
    0.61
    المناصب
    0.60
     übernahm
    0.59
     Furious
    0.59
     vettoriale
    0.58
    ंदीखरीदारी
    0.58
    Act Density 0.254%

    No Known Activations