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

    Neuronpedia

    INDEX
    Explanations

    */

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Whats
    -0.06
     کش
    -0.06
     Run
    -0.06
     тради
    -0.06
    }>
↵
    -0.06
     preached
    -0.06
    aud
    -0.06
    _^
    -0.05
    _intersection
    -0.05
     spider
    -0.05
    POSITIVE LOGITS
     Kyle
    0.07
     Ole
    0.07
     Clover
    0.07
    Ignoring
    0.07
     puberty
    0.07
     varies
    0.07
    *width
    0.07
    اساس
    0.07
    Mayor
    0.06
    /Users
    0.06
    Act Density 0.000%

    No Known Activations