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

    Neuronpedia

    INDEX
    Explanations

    evading capture or detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hostility
    0.61
     hostile
    0.53
     humiliating
    0.49
     ridicule
    0.47
     humiliated
    0.47
     shameful
    0.45
     অপমান
    0.44
     scorn
    0.43
     temptations
    0.43
     opposition
    0.42
    POSITIVE LOGITS
     detection
    1.02
    detection
    0.89
    Detection
    0.88
     capture
    0.87
     Detection
    0.85
     DETECTION
    0.75
    capture
    0.73
     detección
    0.69
     Capture
    0.68
    Capture
    0.66
    Act Density 0.006%

    No Known Activations