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

    Neuronpedia

    INDEX
    Explanations

    See

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    extra
    -0.07
    ابد
    -0.07
    Still
    -0.06
    Ham
    -0.06
    (total
    -0.06
     bard
    -0.06
     vista
    -0.06
     arranging
    -0.06
    dro
    -0.06
    ...)↵↵
    -0.06
    POSITIVE LOGITS
     Germany
    0.08
    .de
    0.08
    mann
    0.07
    ermann
    0.07
    inz
    0.07
    lsruhe
    0.07
     Cologne
    0.07
    üsseldorf
    0.07
     Frankfurt
    0.07
    ß
    0.07
    Act Density 0.696%

    No Known Activations