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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    757
    -0.08
     Rodney
    -0.07
     ##↵
    -0.07
     frequent
    -0.06
     rats
    -0.06
     인간
    -0.06
     surveyed
    -0.06
     Gan
    -0.06
     【
    -0.06
     Kid
    -0.06
    POSITIVE LOGITS
    +xml
    0.07
     maxLength
    0.06
    ComputedStyle
    0.06
    TRGL
    0.06
     objectAtIndex
    0.06
    사람
    0.06
     flattened
    0.06
     arrang
    0.06
     univerz
    0.06
    apixel
    0.06
    Act Density 0.041%

    No Known Activations