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

    Neuronpedia

    INDEX
    Explanations

    time to get/save/complete

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存在的
    0.80
     існу
    0.75
     очень
    0.75
     ጥቅም
    0.73
     дуже
    0.71
     necesarios
    0.66
    ensely
    0.66
    actoring
    0.65
    uller
    0.65
     maneira
    0.64
    POSITIVE LOGITS
    Utf
    0.76
     CC
    0.65
    ？）
    0.65
     yoki
    0.60
     YOUR
    0.59
    𝓑
    0.58
     Bulls
    0.57
    $\$
    0.57
     boo
    0.57
     Ying
    0.57
    Act Density 0.002%

    No Known Activations