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

    Neuronpedia

    INDEX
    Explanations

    AnswerThePublic service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     accused
    0.53
    ハリ
    0.53
    ޑ
    0.46
     diox
    0.46
     atrocious
    0.45
     atrocities
    0.45
     austere
    0.44
    ットン
    0.44
     acclaimed
    0.44
     craz
    0.44
    POSITIVE LOGITS
    Το
    0.50
     το
    0.46
     Το
    0.45
    “
    0.44
    습니다
    0.43
     odpowiedzi
    0.43
     réponse
    0.42
    었습니다
    0.42
    rips
    0.42
    什麼
    0.42
    Act Density 0.003%

    No Known Activations