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

    Neuronpedia

    INDEX
    Explanations

    here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    خن
    0.40
     cancelling
    0.39
    Kwa
    0.38
     pid
    0.38
    пли
    0.37
     ફ
    0.37
     Lifecycle
    0.37
     localizado
    0.37
    bins
    0.36
     tình
    0.36
    POSITIVE LOGITS
    鲑
    0.44
     ake
    0.40
    లె
    0.37
    自家
    0.37
     मोनालिसा
    0.37
    debugElement
    0.36
     Gloria
    0.35
     투
    0.35
    耶
    0.35
    届け
    0.34
    Act Density 0.002%

    No Known Activations