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

    Neuronpedia

    INDEX
    Explanations

    alternatives or contrasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     모든
    0.44
     λόγω
    0.44
    的情况下
    0.43
    问题的
    0.43
     çeşitli
    0.42
    哪些
    0.41
     تط
    0.41
     gelişmeler
    0.41
     इसकी
    0.40
    eniendo
    0.40
    POSITIVE LOGITS
    invite
    0.46
     અથવા
    0.46
     alebo
    0.45
     ወይም
    0.45
    גם
    0.45
    หรือ
    0.44
     veya
    0.43
     conversely
    0.43
    或
    0.43
     antagonism
    0.43
    Act Density 0.006%

    No Known Activations