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

    Neuronpedia

    INDEX
    Explanations

    Zakat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ndrome
    1.79
    hers
    1.78
    ния
    1.58
    hauer
    1.53
    ittal
    1.52
    keun
    1.52
    urization
    1.52
    melding
    1.50
    你需要
    1.50
    cing
    1.49
    POSITIVE LOGITS
    с
    1.94
    есть
    1.80
    ح
    1.73
    дца
    1.66
    வும்
    1.63
     einzige
    1.57
    мії
    1.57
    ी
    1.55
    ्यू
    1.55
    ப
    1.54
    Act Density 0.000%

    No Known Activations