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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and method definitions

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

    function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.78
    httphttps
    -0.74
    MLLoader
    -0.73
     autorytatywna
    -0.73
     AssemblyTitle
    -0.72
     ویکی‌پدی
    -0.72
     Administrativna
    -0.71
     kasarigan
    -0.70
    ftagPool
    -0.69
    تقاوى
    -0.68
    POSITIVE LOGITS
    guenos
    0.34
     tazas
    0.29
     Jehová
    0.29
    ®.
    0.28
     acuer
    0.28
    harapkan
    0.27
     réve
    0.27
     Corée
    0.27
    silueta
    0.26
     proyec
    0.26
    Act Density 0.031%

    No Known Activations