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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mpfr
    -0.07
    olic
    -0.07
     Rahul
    -0.06
    Boston
    -0.06
     feather
    -0.06
    .navigate
    -0.06
     disadvantages
    -0.06
     desde
    -0.06
    _hierarchy
    -0.06
     liter
    -0.06
    POSITIVE LOGITS
    ंस
    0.07
    АТ
    0.07
     awesome
    0.07
    REAM
    0.07
     istem
    0.07
    :
↵
↵
    0.06
    DivElement
    0.06
    貼
    0.06
     بودن
    0.06
     ranking
    0.06
    Act Density 0.031%

    No Known Activations