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

    Neuronpedia

    INDEX
    Explanations

    Okay, enough

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pavattati
    0.48
    ImgBoard
    0.48
    AuthController
    0.47
    APER
    0.47
     Counseling
    0.46
     ショルダー
    0.46
     πλη
    0.45
    BTN
    0.45
     乀
    0.45
    nä
    0.44
    POSITIVE LOGITS
    راهيم
    0.44
     mè
    0.43
     Abe
    0.42
     crib
    0.41
     então
    0.39
     but
    0.39
     Ud
    0.39
     الكربون
    0.38
    football
    0.38
     socialista
    0.38
    Act Density 0.005%

    No Known Activations