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

    Neuronpedia

    INDEX
    Explanations

    od

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alv
    -0.07
     Kavanaugh
    -0.07
    -Th
    -0.06
    踵
    -0.06
    orge
    -0.06
    edge
    -0.06
    unky
    -0.06
    >NN
    -0.06
     wartości
    -0.06
     мобильн
    -0.06
    POSITIVE LOGITS
     emoji
    0.08
     Tiên
    0.07
     AFP
    0.07
     handled
    0.07
     ?",
    0.07
    .assign
    0.06
     rice
    0.06
    ible
    0.06
    负
    0.06
    ysters
    0.06
    Act Density 0.001%

    No Known Activations