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

    Neuronpedia

    INDEX
    Explanations

    databases, dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fidèle
    0.61
     جديدة
    0.61
    ayı
    0.59
    დება
    0.59
    ח
    0.57
    იღ
    0.57
    დე
    0.56
    ו
    0.56
     détails
    0.55
     mousse
    0.54
    POSITIVE LOGITS
    ات
    0.68
    і
    0.63
    ،
    0.63
    и
    0.59
    ，
    0.57
     Со
    0.57
    स
    0.56
    них
    0.55
     pomocí
    0.55
     ibang
    0.54
    Act Density 0.020%

    No Known Activations