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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lộ
    -0.07
     '%
    -0.07
    (Time
    -0.07
     bụi
    -0.06
     Králové
    -0.06
     portrays
    -0.06
     Simulation
    -0.06
     chancellor
    -0.06
    лекс
    -0.06
    (Have
    -0.06
    POSITIVE LOGITS
    AREN
    0.08
    Craig
    0.07
     Craig
    0.07
    کز
    0.07
     FAILURE
    0.07
    iert
    0.06
    #Region
    0.06
     Manga
    0.06
    inar
    0.06
     var
    0.06
    Act Density 0.154%

    No Known Activations