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

    Neuronpedia

    INDEX
    Explanations

    model, formatted text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    suitable
    0.36
     热
    0.36
    oteric
    0.35
     sho
    0.34
    的时候
    0.34
     流
    0.34
     Sho
    0.34
    🌫
    0.34
    th
    0.33
    তি
    0.33
    POSITIVE LOGITS
     фаразлары
    0.41
    लै
    0.41
     MALDI
    0.41
     уйнагыз
    0.40
     creatine
    0.40
     божомолдору
    0.39
     refinance
    0.39
    Ĭ
    0.39
    ジュアル
    0.39
     букмекерлер
    0.38
    Act Density 0.000%

    No Known Activations