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

    Neuronpedia

    INDEX
    Explanations

    say "MIT"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Drawing
    -0.09
    .${
    -0.07
    .[
    -0.07
    ⤇
    -0.07
    ο
    -0.07
    atrix
    -0.07
     Taste
    -0.06
    ű
    -0.06
     ن
    -0.06
     gnome
    -0.06
    POSITIVE LOGITS
     proced
    0.08
    elda
    0.07
    信念
    0.07
    �
    0.07
     مباشرة
    0.07
     cps
    0.07
    bs
    0.07
    حز
    0.07
    oders
    0.07
    ccd
    0.07
    Act Density 0.162%

    No Known Activations