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

    Neuronpedia

    INDEX
    Explanations

    language related to exclusion and its implications

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

    absence or negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.64
     незавершена
    -0.63
     المعيارى
    -0.60
     Comprometido
    -0.54
     TestBed
    -0.54
     HttpNotFound
    -0.52
     ब्रेकडाउन
    -0.50
     tartalomajánló
    -0.50
    GEBURTS
    -0.50
    DMETHOD
    -0.50
    POSITIVE LOGITS
     anstatt
    0.48
     ohne
    0.45
    而不是
    0.43
    Func
    0.41
    backends
    0.41
     while
    0.40
     בלב
    0.40
     zonder
    0.40
     בלי
    0.38
    entliche
    0.38
    Act Density 0.320%

    No Known Activations