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

    Neuronpedia

    INDEX
    Explanations

    to look or seek

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    外出
    0.52
    移動
    0.51
    起身
    0.51
     moveTo
    0.49
     arise
    0.48
    moveTo
    0.46
     move
    0.46
     Move
    0.46
    出行
    0.45
    Move
    0.44
    POSITIVE LOGITS
     inspect
    0.65
    看看
    0.52
     wreak
    0.50
    inspect
    0.48
     witness
    0.46
     greeted
    0.46
     inspection
    0.45
     rekind
    0.45
    寻找
    0.45
     inspected
    0.44
    Act Density 0.015%

    No Known Activations