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

    Neuronpedia

    INDEX
    Explanations

    remaining TRY

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ليات
    0.47
    𒍣
    0.47
    ለጠ
    0.47
    ারিত
    0.44
    <unused15>
    0.43
    眙
    0.43
     élytres
    0.43
    瑆
    0.42
    𐰚
    0.42
    CCCc
    0.42
    POSITIVE LOGITS
     remaining
    0.71
    remaining
    0.64
     оста
    0.60
     remainder
    0.56
     restante
    0.56
    0.56
     остав
    0.55
     Remaining
    0.55
    Remaining
    0.54
     restantes
    0.50
    Act Density 0.059%

    No Known Activations