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

    Neuronpedia

    INDEX
    Explanations

    strip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     operation
    -0.07
     pool
    -0.07
    Capacity
    -0.07
     vitamins
    -0.06
     order
    -0.06
     ownership
    -0.06
    _sigma
    -0.06
     Eggs
    -0.06
    Gal
    -0.06
     beta
    -0.06
    POSITIVE LOGITS
    .strip
    0.07
     stripslashes
    0.07
    마사지
    0.06
     。↵
    0.06
     　　　　　　　　　　　　
    0.06
     Impress
    0.06
     milf
    0.06
    sass
    0.06
     javax
    0.06
     орг
    0.06
    Act Density 0.005%

    No Known Activations