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

    Neuronpedia

    INDEX
    Explanations

    inappropriate content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.95
     costs
    0.92
     protection
    0.86
    il
    0.85
     simple
    0.82
     "
    0.81
     any
    0.80
     helm
    0.79
     conditions
    0.78
     all
    0.77
    POSITIVE LOGITS
     präsent
    1.11
     satirical
    1.09
     treści
    1.09
    🎭
    1.09
     літоў
    1.07
     ప్రేక్షకు
    1.03
    Ņ
    1.03
     اداکار
    1.02
     dźwię
    1.02
    文字列
    1.02
    Act Density 1.801%

    No Known Activations