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

    Neuronpedia

    INDEX
    Explanations

    informative

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LD
    -0.07
    	wx
    -0.06
     Src
    -0.06
    歡
    -0.06
    \E
    -0.06
    Sat
    -0.06
    ЮЛ
    -0.06
    _THREADS
    -0.06
     yorum
    -0.06
    Liquid
    -0.06
    POSITIVE LOGITS
    erry
    0.07
    agog
    0.07
    ERRY
    0.07
     دوم
    0.07
    egra
    0.06
     especialmente
    0.06
    ills
    0.06
     punto
    0.06
    ρίας
    0.06
    ZeroWidthSpace
    0.06
    Act Density 0.010%

    No Known Activations