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

    Neuronpedia

    INDEX
    Explanations

    Chinese characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Grad
    -0.08
     ICT
    -0.07
    _word
    -0.07
     FIT
    -0.07
    -mar
    -0.06
     avan
    -0.06
    FormatException
    -0.06
     milling
    -0.06
    (PRO
    -0.06
    粉
    -0.06
    POSITIVE LOGITS
    ْن
    0.06
     необ
    0.06
    Enviar
    0.06
     noche
    0.06
     pearl
    0.06
    ULD
    0.06
     tăng
    0.06
     Alvarez
    0.05
    ैज
    0.05
    เคย
    0.05
    Act Density 0.022%

    No Known Activations