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

    Neuronpedia

    INDEX
    Explanations

    static

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    酸
    -0.06
     jež
    -0.06
     alphabetical
    -0.06
    Rated
    -0.06
    (GUI
    -0.06
     alertController
    -0.06
    以及
    -0.06
    Loss
    -0.06
     повин
    -0.06
    통신
    -0.06
    POSITIVE LOGITS
     sab
    0.07
     servant
    0.06
    otope
    0.06
    oko
    0.06
     enrich
    0.06
     Sab
    0.06
    на
    0.06
    stories
    0.06
     maxim
    0.06
     Security
    0.06
    Act Density 0.001%

    No Known Activations