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

    Neuronpedia

    INDEX
    Explanations

    rarely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fon
    -0.07
     hurt
    -0.07
     Keys
    -0.06
     Celsius
    -0.06
     BAD
    -0.06
     EM
    -0.06
    .BOLD
    -0.06
     Jab
    -0.06
    =my
    -0.06
    hf
    -0.06
    POSITIVE LOGITS
     girişim
    0.07
    asar
    0.07
     trưởng
    0.06
    ●●
    0.06
    概念
    0.06
    Ÿ
    0.06
    Require
    0.06
     annihil
    0.06
    ่วม
    0.06
    omnia
    0.06
    Act Density 0.001%

    No Known Activations