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

    Neuronpedia

    INDEX
    Explanations

    Categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slic
    -0.06
     par
    -0.06
     superv
    -0.06
     manages
    -0.06
     difer
    -0.06
    [word
    -0.06
    kům
    -0.06
    atively
    -0.06
    grade
    -0.06
    реп
    -0.06
    POSITIVE LOGITS
    /><
    0.06
    =str
    0.06
    是一
    0.06
     Iz
    0.06
    —I
    0.06
    Ron
    0.06
    Dear
    0.06
    CancelButton
    0.06
    ="../
    0.06
     Ron
    0.06
    Act Density 0.034%

    No Known Activations