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

    Neuronpedia

    INDEX
    Explanations

    Fantasy storytelling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prop
    -0.06
     년도별
    -0.06
    ULA
    -0.06
     přísluš
    -0.06
     Мик
    -0.06
     suff
    -0.06
    Invariant
    -0.06
    ВО
    -0.06
    ..↵↵↵↵
    -0.06
    ？”↵↵
    -0.06
    POSITIVE LOGITS
     espect
    0.08
     Payment
    0.07
     careg
    0.07
     bạn
    0.06
    ině
    0.06
    tener
    0.06
    ыт
    0.06
    (latitude
    0.06
    чини
    0.06
     ofrece
    0.06
    Act Density 0.008%

    No Known Activations