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
    stars
    -0.07
    orary
    -0.07
    _routes
    -0.06
     drivers
    -0.06
    -Level
    -0.06
    fitness
    -0.06
    .vo
    -0.06
     Boost
    -0.06
     brushing
    -0.06
     barrage
    -0.06
    POSITIVE LOGITS
    Haunted
    0.07
     登
    0.07
    ”。↵↵
    0.07
    /gr
    0.07
     Andr
    0.06
    0.06
     کمتر
    0.06
     manos
    0.06
    _SUM
    0.06
    。”↵↵
    0.06
    Act Density 0.009%

    No Known Activations