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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coded
    -0.07
     subscribed
    -0.06
     DISABLE
    -0.06
    핀
    -0.06
    stars
    -0.06
    melon
    -0.06
    794
    -0.06
    /Header
    -0.06
     усл
    -0.06
     itm
    -0.06
    POSITIVE LOGITS
    .actor
    0.07
    split
    0.07
     truck
    0.06
     Familie
    0.06
    voy
    0.06
    杉
    0.06
     Jenna
    0.06
     vibrations
    0.06
    .bio
    0.06
     Ron
    0.06
    Act Density 0.001%

    No Known Activations