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

    Neuronpedia

    INDEX
    Explanations

    discourse markers and structural phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.53
    ھی
    0.46
     RESOL
    0.46
     CIVIL
    0.46
    Numeral
    0.44
     Coordin
    0.43
     POLICY
    0.43
     هی
    0.43
    င
    0.42
    ጄ
    0.42
    POSITIVE LOGITS
     博文
    0.51
    ensburg
    0.46
    apache
    0.45
    blast
    0.45
    net
    0.44
    linker
    0.44
    sphere
    0.43
     enige
    0.41
    abuse
    0.41
    msub
    0.40
    Act Density 0.002%

    No Known Activations