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
    amı
    -0.07
     formally
    -0.06
     likely
    -0.06
     Here
    -0.06
    �
    -0.06
     emperor
    -0.06
     Azerbaijan
    -0.06
    як
    -0.06
     concrete
    -0.06
     obsah
    -0.06
    POSITIVE LOGITS
    coder
    0.08
     nguy
    0.07
     calibrated
    0.07
    сих
    0.06
     mongo
    0.06
     QUI
    0.06
    ت
    0.06
    ("")
    0.06
    JOR
    0.06
    ((
    0.06
    Act Density 0.000%

    No Known Activations