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

    Neuronpedia

    INDEX
    Explanations

    launching operations or battles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     жет
    0.76
     לך
    0.75
    在你
    0.74
     соответ
    0.74
     matroid
    0.74
    ichever
    0.73
     besitzen
    0.73
    hältnisse
    0.72
     entsprechen
    0.72
     пределах
    0.72
    POSITIVE LOGITS
     spearheaded
    2.30
     initiated
    2.07
     undertaken
    2.02
     aimed
    1.98
     instigated
    1.87
     led
    1.82
     launched
    1.80
     conducted
    1.74
     begun
    1.70
     orchestrated
    1.70
    Act Density 0.267%

    No Known Activations