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

    Neuronpedia

    INDEX
    Explanations

    percentages, units, and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     전체
    0.38
     존재
    0.37
    琰
    0.37
     Actual
    0.37
    （
    0.37
     Min
    0.37
     Welche
    0.35
    [
    0.35
    Atual
    0.35
    /
    0.34
    POSITIVE LOGITS
     ebenfalls
    0.50
    uiDesigner
    0.43
    俦
    0.39
     tiež
    0.39
    grove
    0.39
    стал
    0.38
    ವರಿ
    0.38
    ariales
    0.38
    同樣
    0.38
    reproductive
    0.38
    Act Density 0.081%

    No Known Activations