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

    Neuronpedia

    INDEX
    Explanations

    words associated with legal terms and conditions

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

    ending in specific suffixes

    np_acts-logits-general · gemini-2.0-flash

    RESPONSibilities and opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pe
    -0.46
    jing
    -0.45
    ji
    -0.45
    AIRES
    -0.45
    res
    -0.45
    LLABLE
    -0.44
    zes
    -0.43
    jos
    -0.42
    ja
    -0.42
    dia
    -0.41
    POSITIVE LOGITS
     Roskov
    0.92
    انيف
    0.86
    RTEE
    0.83
     betweenstory
    0.82
     EconPapers
    0.82
    EDEFAULT
    0.75
    Personensuche
    0.74
     nahilalakip
    0.74
    DeleteBehavior
    0.73
    AND
    0.71
    Act Density 0.510%

    No Known Activations