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

    Neuronpedia

    INDEX
    Explanations

    legal and business contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.55
     आणि
    0.50
    -
    0.50
    ‑
    0.44
     và
    0.44
     disampaikan
    0.43
    和
    0.43
     variously
    0.42
    や
    0.42
     buildings
    0.41
    POSITIVE LOGITS
     შემთხვევაში
    0.47
     제외
    0.46
    슭
    0.46
    ר
    0.46
     რომელი
    0.46
     хоть
    0.45
     henceforth
    0.45
     스스로
    0.45
     wyłącznie
    0.44
    Usage
    0.44
    Act Density 0.047%

    No Known Activations