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

    Neuronpedia

    INDEX
    Explanations

    harmful or harmless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ส์
    0.90
     capas
    0.86
    ंठ
    0.85
    зів
    0.84
    chn
    0.84
    pture
    0.81
     Malone
    0.79
    erit
    0.79
     подар
    0.78
     Patagonia
    0.77
    POSITIVE LOGITS
     তব
    0.92
    ⃝
    0.92
    써
    0.91
     obrig
    0.90
    ብዙ
    0.87
    િક્
    0.87
     imprescind
    0.87
     essentiels
    0.86
    ım
    0.86
     Pero
    0.86
    Act Density 0.030%

    No Known Activations