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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    licity
    -0.07
     Funny
    -0.07
    lev
    -0.06
     Render
    -0.06
    TEGR
    -0.06
     Brushes
    -0.06
     Ful
    -0.06
    GRA
    -0.06
     babys
    -0.06
    缓
    -0.06
    POSITIVE LOGITS
    /id
    0.07
     трудов
    0.07
     ساخته
    0.06
     BadRequest
    0.06
     اصول
    0.06
    clarations
    0.06
     Colors
    0.06
     em
    0.06
     роботу
    0.06
     Equation
    0.06
    Act Density 0.001%

    No Known Activations