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

    Neuronpedia

    INDEX
    Explanations

    numerical values or sequences

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

    non-english characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "}")
    -0.35
    تقاوى
    -0.29
    \
    -0.28
    ;
    -0.28
    wsze
    -0.27
    ",
    -0.27
     menem
    -0.26
     Capitán
    -0.26
    mak
    -0.26
     aufs
    -0.26
    POSITIVE LOGITS
    دانشنامهٔ
    0.90
     esternos
    0.80
     للمعارف
    0.77
     lenker
    0.77
     itſelf
    0.75
     fashiola
    0.73
    حياتها
    0.71
     ſche
    0.71
    <unused43>
    0.71
    <unused3>
    0.71
    Act Density 0.099%

    No Known Activations