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

    Neuronpedia

    INDEX
    Explanations

    respect or politeness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    O
    0.52
     davvero
    0.50
     massimo
    0.50
     overhear
    0.47
    iglia
    0.45
     quanta
    0.44
     protagonist
    0.43
    ogliere
    0.43
     ovviamente
    0.43
     lasci
    0.43
    POSITIVE LOGITS
    '}).
    0.50
     页
    0.46
     }).
    0.45
    тира
    0.45
    謂
    0.44
     aboriginal
    0.42
    冷却
    0.42
    ecological
    0.42
    엷
    0.41
    뛴
    0.41
    Act Density 0.001%

    No Known Activations