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

    Neuronpedia

    INDEX
    Explanations

    categories and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    люб
    0.43
    FBSDKInternal
    0.41
    ťa
    0.38
    ulie
    0.38
    rtol
    0.37
    疖
    0.37
     trúc
    0.37
    gráf
    0.37
     எல்ல
    0.37
     иң
    0.37
    POSITIVE LOGITS
     cowboys
    0.39
     Razor
    0.39
     Alvin
    0.38
     தவ
    0.38
     Springer
    0.38
     zaw
    0.38
     Adonis
    0.37
     Gavin
    0.37
     arte
    0.37
     अड
    0.36
    Act Density 0.000%

    No Known Activations