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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations/derivations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     civic
    -0.07
    Sea
    -0.07
     combust
    -0.07
     Customer
    -0.07
    Ale
    -0.06
    _*
    -0.06
     Кат
    -0.06
     gravitational
    -0.06
    RenderingContext
    -0.06
    .leave
    -0.06
    POSITIVE LOGITS
    หญ
    0.08
    alon
    0.08
    ，但是
    0.07
    prix
    0.06
    _VAL
    0.06
    SectionsIn
    0.06
    .anim
    0.06
    dropdown
    0.06
    balanced
    0.06
    ız
    0.06
    Act Density 0.055%

    No Known Activations