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

    Neuronpedia

    INDEX
    Explanations

    describing specific concepts and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     கோட்ப
    0.43
     coû
    0.40
     Chirurg
    0.40
     scanners
    0.40
     déf
    0.39
     äußerst
    0.39
    挺
    0.39
    頗
    0.38
    czaj
    0.38
    친구
    0.38
    POSITIVE LOGITS
    embangan
    0.46
     Us
    0.41
    ,{
    0.40
    Us
    0.40
    OPEN
    0.39
     حسن
    0.39
     있게
    0.38
     change
    0.38
     changes
    0.37
    WS
    0.36
    Act Density 0.000%

    No Known Activations