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

    Neuronpedia

    INDEX
    Explanations

    external resource links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Chord
    0.33
     Рус
    0.31
     Bryce
    0.31
    Patch
    0.31
     affirmed
    0.30
    Grade
    0.30
    _\
    0.30
    Cheat
    0.30
    Pierce
    0.29
    Term
    0.29
    POSITIVE LOGITS
     fera
    0.31
     наличие
    0.31
     ovu
    0.31
    當然
    0.30
    мпания
    0.30
     базы
    0.29
    舉
    0.29
     edgy
    0.29
    жений
    0.29
    ดับ
    0.28
    Act Density 0.004%

    No Known Activations