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

    Neuronpedia

    INDEX
    Explanations

    measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rey
    -0.06
     :.|
    -0.06
     zvyš
    -0.06
     Üniversit
    -0.06
    CAP
    -0.06
     назна
    -0.06
     zim
    -0.06
    ';↵↵↵↵
    -0.06
    Newsletter
    -0.06
    oldemort
    -0.06
    POSITIVE LOGITS
     slightly
    0.06
    GB
    0.06
    طب
    0.06
     Individual
    0.06
     kterým
    0.06
    ійного
    0.06
    No
    0.06
    _Begin
    0.06
    CONDS
    0.06
    eného
    0.06
    Act Density 0.008%

    No Known Activations