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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }`;↵↵
    -0.08
    covery
    -0.07
     verb
    -0.07
     parser
    -0.06
     Star
    -0.06
     pointers
    -0.06
    _Arg
    -0.06
    anc
    -0.06
     scenarios
    -0.06
     mature
    -0.06
    POSITIVE LOGITS
    无码
    0.07
    恒
    0.06
     converted
    0.06
     พร
    0.06
    830
    0.06
    金
    0.06
    .patch
    0.06
    Wins
    0.06
    有限
    0.06
     จำก
    0.06
    Act Density 0.027%

    No Known Activations