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

    Neuronpedia

    INDEX
    Explanations

    executing operations or data ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ща
    0.42
    atchewan
    0.41
    *,
    0.41
    蘞
    0.41
    或者
    0.40
    妨
    0.40
     Conversely
    0.40
     बृ
    0.39
    ዃ
    0.39
    的使用
    0.39
    POSITIVE LOGITS
     pièce
    0.46
     pik
    0.46
    realm
    0.45
     devlet
    0.45
     probleme
    0.45
     ktoś
    0.44
     da
    0.43
     dzie
    0.43
    Valor
    0.43
     kär
    0.43
    Act Density 0.000%

    No Known Activations