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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    clar
    -0.07
     incor
    -0.06
    ynchronization
    -0.06
    gfx
    -0.06
     paging
    -0.06
     oval
    -0.06
    .Percent
    -0.06
    _air
    -0.06
    Saved
    -0.06
    apol
    -0.06
    POSITIVE LOGITS
     Firearms
    0.07
     Symptoms
    0.07
    َّ
    0.07
    typically
    0.07
     italia
    0.07
    August
    0.07
     Sexe
    0.06
     mice
    0.06
    @Data
    0.06
    李
    0.06
    Act Density 0.016%

    No Known Activations