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

    Neuronpedia

    INDEX
    Explanations

    expert consensus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     curioso
    0.44
     للنساء
    0.42
    водитель
    0.42
    ändert
    0.41
     당신
    0.41
     Shame
    0.41
     Populations
    0.40
    vetica
    0.39
     {:?}",
    0.39
    ),],
    0.39
    POSITIVE LOGITS
     experts
    1.74
    experts
    1.58
     analysts
    1.57
    Experts
    1.48
     Experts
    1.44
     expertos
    1.42
     экспер
    1.41
    专家
    1.40
     전문가
    1.40
     विशेषज्ञों
    1.37
    Act Density 0.031%

    No Known Activations