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

    Neuronpedia

    INDEX
    Explanations

    code import statements with double quote delimited strings

    oai_token-act-pair · gemini-2.0-flash

    programming keywords or terms

    np_token-act-pair-logits · gpt-4o-mini

    code/files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    finden
    -0.48
     virke
    -0.47
     برانيه
    -0.45
    UpInside
    -0.45
    mäß
    -0.43
     délic
    -0.42
    Predecesor
    -0.42
    CSRF
    -0.42
    annelse
    -0.42
    licants
    -0.42
    POSITIVE LOGITS
    enterOuterAlt
    0.71
    المناصب
    0.69
     thiệu
    0.67
    boxylic
    0.65
    مصادر
    0.64
    BeginContext
    0.63
    makeConstraints
    0.59
     poveznice
    0.59
    verwijspagina
    0.58
    himu
    0.57
    Act Density 0.504%

    No Known Activations