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

    Neuronpedia

    INDEX
    Explanations

    security exploits or malware behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लौटने
    0.46
     hvis
    0.45
     wenn
    0.44
     kleine
    0.42
     företag
    0.42
     Glückwunsch
    0.41
     eğer
    0.41
     mooie
    0.41
     모든
    0.41
     اگر
    0.40
    POSITIVE LOGITS
     eingesetzt
    0.39
     eingestellt
    0.37
     ron
    0.35
     bearbeitet
    0.34
     zu
    0.32
     hinzuge
    0.32
     im
    0.31
     sacrificed
    0.31
     einge
    0.31
    ceries
    0.31
    Act Density 0.016%

    No Known Activations