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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cadena
    -0.07
     Rock
    -0.06
     Fair
    -0.06
     ammunition
    -0.06
     Next
    -0.06
     LLP
    -0.06
    Occ
    -0.06
    _Line
    -0.06
    מ
    -0.06
     jump
    -0.06
    POSITIVE LOGITS
     **/
↵
    0.06
     �
    0.06
     pus
    0.06
    (CONFIG
    0.06
     нія
    0.06
     zbyt
    0.06
     tweeting
    0.06
     дея
    0.06
    xcf
    0.06
    }/#{
    0.06
    Act Density 0.001%

    No Known Activations