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

    Neuronpedia

    INDEX
    Explanations

    E-Tech Electric, analysis, constantly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IN
    1.04
    ’
    0.98
    soever
    0.96
    ள்ளார்
    0.95
    ucos
    0.95
    O
    0.94
    Voor
    0.92
    tion
    0.90
    ⤒
    0.89
    ↵
    0.87
    POSITIVE LOGITS
     sekaligus
    0.81
    лки
    0.79
     ಹಾಗೂ
    0.79
    াত্মক
    0.78
     lahan
    0.78
    ပြီး
    0.77
    ßt
    0.77
     Bereiche
    0.76
     railroads
    0.76
    ist
    0.75
    Act Density 0.714%

    No Known Activations