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

    Neuronpedia

    INDEX
    Explanations

    medical conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     모든
    0.47
     전류
    0.46
     못
    0.44
     ordre
    0.43
    erre
    0.42
     عدم
    0.42
     سبب
    0.42
    原因
    0.41
     스스로
    0.41
     경우
    0.41
    POSITIVE LOGITS
     Hao
    0.46
     mewah
    0.45
     armado
    0.45
    డం
    0.42
     Travelers
    0.42
     khá
    0.42
     Champs
    0.42
    aki
    0.42
     Tourists
    0.42
    rcParams
    0.41
    Act Density 0.002%

    No Known Activations