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

    Neuronpedia

    INDEX
    Explanations

    taser and electrical stun devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Alignment
    0.45
    alignment
    0.45
     Mag
    0.43
    Ó
    0.42
    Al
    0.40
    Mag
    0.40
    Terry
    0.40
     Alignment
    0.39
    Survivor
    0.39
     रेगु
    0.38
    POSITIVE LOGITS
     TAS
    0.48
     stunned
    0.46
     stun
    0.46
     probe
    0.45
     tas
    0.44
     darts
    0.44
     probed
    0.44
     Tas
    0.43
     probes
    0.42
     ظاهر
    0.41
    Act Density 0.002%

    No Known Activations