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

    Neuronpedia

    INDEX
    Explanations

    marketing name given

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    橹
    0.85
     ακόμη
    0.78
     akşam
    0.77
    πο
    0.75
    Saat
    0.75
     początku
    0.74
    ST
    0.72
    tain
    0.71
     问题
    0.70
    તાં
    0.69
    POSITIVE LOGITS
    ссы
    0.89
    ل
    0.84
     основы
    0.78
    ляются
    0.77
    젖
    0.77
    គឺ
    0.75
     savk
    0.74
    ्यर
    0.73
    ườ
    0.71
    словно
    0.71
    Act Density 0.000%

    No Known Activations