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

    Neuronpedia

    INDEX
    Explanations

    references to scholarly articles or citations

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

    et al. citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.42
     čierna
    -0.40
     ��
    -0.39
     مرئيه
    -0.38
     独
    -0.37
    uled
    -0.37
    المشاركات
    -0.36
    — 
    -0.36
    独
    -0.35
     yı
    -0.35
    POSITIVE LOGITS
    ########.
    0.53
     Administrativna
    0.52
    AndEndTag
    0.49
     Comprometido
    0.45
     useAppContext
    0.45
     jointly
    0.44
    几位
    0.44
    ፩
    0.43
    几人
    0.42
     indisponible
    0.42
    Act Density 0.047%

    No Known Activations