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

    Neuronpedia

    INDEX
    Explanations

    includes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     keluar
    0.67
    接著
    0.66
     incluyendo
    0.65
     including
    0.64
     тә
    0.63
    ﺴ
    0.63
     саны
    0.63
     intertw
    0.62
    存在的
    0.61
    会出现
    0.61
    POSITIVE LOGITS
     ضمن
    1.00
    បញ្ចូល
    0.88
     dalamnya
    0.87
     dentro
    0.86
     therein
    0.81
     dedans
    0.75
     herein
    0.73
    めた
    0.73
    ضمن
    0.73
     сюда
    0.71
    Act Density 0.044%

    No Known Activations