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

    Neuronpedia

    INDEX
    Explanations

    ri

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sylvania
    -0.07
    .sm
    -0.07
    getClass
    -0.06
    .prevent
    -0.06
     Apps
    -0.06
    (val
    -0.06
    chè
    -0.06
    .Env
    -0.06
    -page
    -0.06
    英特尔
    -0.06
    POSITIVE LOGITS
    >Password
    0.07
     UPLOAD
    0.07
    uisine
    0.07
     toaster
    0.07
    лан
    0.07
    牲
    0.06
     homemade
    0.06
     killings
    0.06
     frauen
    0.06
     بواس
    0.06
    Act Density 0.001%

    No Known Activations