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

    Neuronpedia

    INDEX
    Explanations

    confidence or love

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     файла
    0.64
     ඉතා
    0.64
     Bộ
    0.63
     classifier
    0.63
     impractic
    0.62
    简称
    0.62
     olyan
    0.61
    历史上
    0.61
     Hausdorff
    0.60
     danneggi
    0.59
    POSITIVE LOGITS
    ความ
    1.01
     ความ
    0.86
    ຄວາມ
    0.81
     confiança
    0.71
     confianza
    0.70
     sự
    0.70
     entusiasmo
    0.65
    amour
    0.64
     sức
    0.64
    วาม
    0.63
    Act Density 0.236%

    No Known Activations