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

    Neuronpedia

    INDEX
    Explanations

    Text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pretext
    -0.07
     lễ
    -0.07
     invade
    -0.07
    629
    -0.06
    Є
    -0.06
     Sın
    -0.06
    推
    -0.06
    bread
    -0.06
     الرو
    -0.06
     Sunni
    -0.06
    POSITIVE LOGITS
    _unref
    0.06
    redux
    0.06
    .enums
    0.06
    .Repositories
    0.06
    stem
    0.06
    (md
    0.06
    .Connect
    0.06
    (img
    0.06
    -create
    0.06
    -auth
    0.06
    Act Density 0.005%

    No Known Activations