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

    Neuronpedia

    INDEX
    Explanations

    references to programming code and technical definitions

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

    #define directives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.98
    Datuak
    -0.88
    endphp
    -0.83
    Personendaten
    -0.79
    RenderAtEndOf
    -0.78
    webElementXpaths
    -0.75
     tartalomajánló
    -0.74
    脚注の使い方
    -0.74
    providedIn
    -0.73
    httphttps
    -0.72
    POSITIVE LOGITS
    .
    0.35
     halbe
    0.33
     rangement
    0.32
     Royaume
    0.32
     Konsequ
    0.31
     rather
    0.29
    。
    0.29
     outils
    0.29
    ;
    0.28
    2
    0.28
    Act Density 0.057%

    No Known Activations