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

    Neuronpedia

    INDEX
    Explanations

    timing of events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    特点
    0.43
    linic
    0.41
    UID
    0.39
     orderService
    0.38
    वधान
    0.38
    络
    0.38
    anku
    0.37
    ongen
    0.37
    安全
    0.37
    〞
    0.37
    POSITIVE LOGITS
     św
    0.52
     inwest
    0.49
    د
    0.47
    ziest
    0.47
     sperm
    0.46
     Venus
    0.46
     Aristotle
    0.46
     Atlantis
    0.46
    礦
    0.46
     mine
    0.45
    Act Density 0.001%

    No Known Activations