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

    Neuronpedia

    INDEX
    Explanations

    facts about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ทีม
    0.39
     Adjustable
    0.39
     চ্যানেল
    0.38
     ലഭ്യ
    0.38
    じる
    0.37
     بین
    0.37
     mantienen
    0.37
    forcement
    0.36
     Combined
    0.36
     Tard
    0.36
    POSITIVE LOGITS
     आल्सो
    0.44
     occult
    0.43
     attacked
    0.42
    كلمنا
    0.41
    名叫
    0.41
    比如说
    0.41
    creva
    0.40
    比如說
    0.40
    或其他
    0.40
    thisTrack
    0.40
    Act Density 0.001%

    No Known Activations