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

    Neuronpedia

    INDEX
    Explanations

    plot summaries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    꿕
    -0.09
    .tip
    -0.08
    怡
    -0.07
    :image
    -0.07
    怦
    -0.07
     مواضيع
    -0.07
    _images
    -0.07
    端午
    -0.07
    _ROUT
    -0.07
     يتعلق
    -0.07
    POSITIVE LOGITS
     HP
    0.07
     substantive
    0.07
    贮
    0.07
     horsepower
    0.06
     drop
    0.06
     ко
    0.06
    都会
    0.06
     XO
    0.06
     SHR
    0.06
     internationally
    0.06
    Act Density 0.047%

    No Known Activations