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

    Neuronpedia

    INDEX
    Explanations

    weapons and warfare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     explosive
    0.64
     বোমা
    0.62
     Bomb
    0.61
     bomb
    0.59
     deadly
    0.54
    Bomb
    0.53
     bomba
    0.53
     lethal
    0.52
     bombas
    0.51
     explosives
    0.51
    POSITIVE LOGITS
     discharge
    0.54
     ACTIVITY
    0.49
     discharged
    0.48
     activity
    0.45
     blasts
    0.44
     Activity
    0.43
     blast
    0.43
    Action
    0.42
    Activity
    0.41
    discharge
    0.41
    Act Density 0.010%

    No Known Activations