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

    Neuronpedia

    INDEX
    Explanations

    clinical equipoise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enderung
    0.46
    azoline
    0.41
    جمع
    0.41
     भूमिका
    0.40
     Childhood
    0.39
     Мар
    0.39
     продуктов
    0.39
    𝘥
    0.39
    წი
    0.38
    落在
    0.38
    POSITIVE LOGITS
     achieve
    0.43
     хвати
    0.42
    以上
    0.41
     escalate
    0.41
     lashed
    0.40
    meV
    0.40
     able
    0.40
     sunk
    0.40
    χω
    0.39
    לה
    0.39
    Act Density 0.009%

    No Known Activations