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

    Neuronpedia

    INDEX
    Explanations

    possibility/suggestion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hwy
    -0.07
    incip
    -0.07
     Creatures
    -0.06
     +=
    -0.06
     Knight
    -0.06
     Qt
    -0.06
     Transparent
    -0.06
    んでいる
    -0.06
    regions
    -0.06
     Narrative
    -0.06
    POSITIVE LOGITS
     povol
    0.07
    _rat
    0.07
    ）：
    0.06
     지원
    0.06
     entreprise
    0.06
    );
↵
↵
    0.06
    买
    0.06
    不要
    0.06
     разреш
    0.06
     flashlight
    0.06
    Act Density 0.020%

    No Known Activations