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

    Neuronpedia

    INDEX
    Explanations

    your + action/outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    本身的
    0.48
     sendiri
    0.45
     persönlichen
    0.41
     особы
    0.40
    了自己的
    0.40
    qualität
    0.40
    本身
    0.40
    自身
    0.39
     особенности
    0.39
     частности
    0.38
    POSITIVE LOGITS
     actions
    0.68
     findings
    0.59
     choices
    0.52
     observations
    0.50
     efforts
    0.46
     approach
    0.46
     activity
    0.46
     действий
    0.46
     choice
    0.45
     target
    0.45
    Act Density 0.015%

    No Known Activations