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

    Neuronpedia

    INDEX
    Explanations

    shooting, gunfire, or violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chor
    -0.81
     effetto
    -0.78
     εγ
    -0.77
    CHOR
    -0.76
    反应
    -0.76
     burner
    -0.75
    burner
    -0.75
    SceneManager
    -0.73
     espressione
    -0.73
     conoscenza
    -0.73
    POSITIVE LOGITS
     rampage
    1.08
     shooting
    0.94
     indiscriminate
    0.91
     shootings
    0.88
    random
    0.85
     randomly
    0.83
     RANDOM
    0.81
     random
    0.80
    rody
    0.74
    Random
    0.71
    Act Density 0.035%

    No Known Activations