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

    Neuronpedia

    INDEX
    Explanations

    malicious code or software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    耂
    0.45
    論
    0.45
     رئیس
    0.44
     уголов
    0.44
    菂
    0.43
     सार्वजनिक
    0.42
    場面積
    0.42
    議題
    0.42
    堌
    0.42
     Kyung
    0.41
    POSITIVE LOGITS
     coach
    0.65
     coaching
    0.64
     coaches
    0.61
     jerseys
    0.56
    教练
    0.56
     athlete
    0.54
     teammate
    0.54
     coached
    0.54
     softball
    0.53
     prep
    0.52
    Act Density 0.000%

    No Known Activations