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

    Neuronpedia

    INDEX
    Explanations

    occurrences of comments in code

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

    code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imprimée
    -0.51
    PerformLayout
    -0.51
     démocr
    -0.49
     antigüedad
    -0.48
     desmotivaciones
    -0.47
     škoda
    -0.44
     anún
    -0.44
    secuencias
    -0.44
     hemsida
    -0.43
     hjälp
    -0.43
    POSITIVE LOGITS
    ){//
    0.66
     autorytatywna
    0.65
    Autoritní
    0.65
    {//
    0.64
    OGND
    0.61
     يتيمه
    0.60
     {//
    0.59
    脚注の使い方
    0.56
     kasarigan
    0.56
    ArgumentParser
    0.55
    Act Density 0.021%

    No Known Activations