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

    Neuronpedia

    INDEX
    Explanations

    buy on, API gateway, keeping morale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.47
    кты
    0.43
    ID
    0.42
    ی
    0.42
    ג
    0.41
     Nazionale
    0.40
    （
    0.40
     ID
    0.39
    onite
    0.39
    ）
    0.39
    POSITIVE LOGITS
     sencilla
    0.45
    闸
    0.43
     الأم
    0.40
    ្នក
    0.39
     phường
    0.39
     consigui
    0.39
     plufieurs
    0.39
    đe
    0.38
     jornadas
    0.38
    ாமல்
    0.37
    Act Density 0.000%

    No Known Activations