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

    Neuronpedia

    INDEX
    Explanations

    cell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    护身
    -0.07
    曙光
    -0.07
    竫
    -0.07
    Tên
    -0.06
    pany
    -0.06
    emme
    -0.06
    所示
    -0.06
    휙
    -0.06
    Foto
    -0.06
     genetic
    -0.06
    POSITIVE LOGITS
     //*
    0.07
     excellence
    0.07
     revolver
    0.07
     bulb
    0.07
    ecz
    0.07
     Downing
    0.07
     immoral
    0.07
     sher
    0.07
     Horm
    0.07
    .va
    0.07
    Act Density 0.000%

    No Known Activations