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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names

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

    starting with "Fil", "Sil", "Gil", "Hil" or "pil"

    np_acts-logits-general · gemini-2.0-flash

    words ending in 'il' followed by common suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    -0.58
     trời
    -0.58
    ngdoc
    -0.56
    ERAS
    -0.53
    Carriera
    -0.50
     Exacts
    -0.49
    ecap
    -0.48
     whole
    -0.47
    ities
    -0.47
    llon
    -0.47
    POSITIVE LOGITS
     فريبيس
    0.58
    licon
    0.49
    saraba
    0.49
    bert
    0.49
    multer
    0.48
    randomUUID
    0.47
     indipendente
    0.46
    ChildIndex
    0.46
    ADELPHIA
    0.46
     specialmente
    0.45
    Act Density 0.117%

    No Known Activations