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

    Neuronpedia

    INDEX
    Explanations

    puzzles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     staining
    -0.07
    Plain
    -0.06
     पड़
    -0.06
     questo
    -0.06
    ادم
    -0.06
    (package
    -0.06
     Corrections
    -0.06
    dateTime
    -0.06
    abad
    -0.06
     hundred
    -0.06
    POSITIVE LOGITS
     модель
    0.06
     gibt
    0.06
    вок
    0.06
       
    0.06
    _Comm
    0.06
    에도
    0.06
     вик
    0.06
     dort
    0.06
    (Rect
    0.06
     И
    0.06
    Act Density 0.014%

    No Known Activations