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

    Neuronpedia

    INDEX
    Explanations

    attacks and war scenarios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ладу
    -0.06
     pedestal
    -0.06
    573
    -0.06
     Pop
    -0.06
    210
    -0.06
    Sl
    -0.06
     frem
    -0.06
     Marble
    -0.06
     ده
    -0.06
    969
    -0.06
    POSITIVE LOGITS
     ป
    0.07
    รรม
    0.07
    	dis
    0.07
    мі
    0.07
    .unsubscribe
    0.06
    _ss
    0.06
    ís
    0.06
    (dis
    0.06
    _]
    0.06
    _ET
    0.06
    Act Density 0.093%

    No Known Activations