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

    Neuronpedia

    INDEX
    Explanations

    be indicative of harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thed
    0.39
    the
    0.34
     ਸਮ
    0.33
    verbrauch
    0.33
    ुल्लाह
    0.33
    ून
    0.30
    رسٹ
    0.30
    ಿರುವ
    0.30
    robin
    0.29
     ブリ
    0.29
    POSITIVE LOGITS
     a
    0.44
     dific
    0.41
     боли
    0.41
    o
    0.41
    스
    0.41
    в
    0.41
    ني
    0.40
    s
    0.40
    í
    0.39
     bolesti
    0.39
    Act Density 0.251%

    No Known Activations