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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming functions and procedures

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

    Non-English language related

    np_acts-logits-general · gemini-2.0-flash

    language suffixes and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    를
    -1.10
    와
    -1.04
    는
    -0.96
    가
    -0.85
    rungsseite
    -0.83
     kasarigan
    -0.77
     незавершена
    -0.76
    __*/
    -0.76
    MemoryWarning
    -0.74
    라는
    -0.74
    POSITIVE LOGITS
    nya
    1.18
    ها
    0.76
    ness
    0.76
    ם
    0.74
    ın
    0.74
    le
    0.74
    lo
    0.73
    los
    0.70
    la
    0.67
    ه
    0.67
    Act Density 0.039%

    No Known Activations