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

    Neuronpedia

    INDEX
    Explanations

    multilingual words or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    酆
    0.43
    тика
    0.41
    FANG
    0.41
    滅
    0.41
    phenyl
    0.40
    ಲಿಯ
    0.40
     لی
    0.39
     ባለ
    0.39
    Phenyl
    0.39
    गाने
    0.39
    POSITIVE LOGITS
     enthalten
    0.45
    PS
    0.43
     poskyt
    0.43
     anv
    0.41
     Cry
    0.41
     montre
    0.41
     nah
    0.41
    呦
    0.41
     flere
    0.41
     valam
    0.41
    Act Density 0.000%

    No Known Activations