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

    Neuronpedia

    INDEX
    Explanations

    physical harm or accidents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ರಿಕ
    0.43
    ız
    0.42
    都會
    0.41
     Until
    0.40
    ដែលមាន
    0.40
    aik
    0.39
    ত্তি
    0.39
     Thou
    0.39
    쵸
    0.39
     मोहन
    0.38
    POSITIVE LOGITS
     during
    0.54
     collisions
    0.52
     acidente
    0.50
     accidente
    0.49
     wars
    0.48
     DURING
    0.47
     আঘাতে
    0.46
    ในการ
    0.46
     accidents
    0.46
     В
    0.45
    Act Density 0.025%

    No Known Activations