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

    Neuronpedia

    INDEX
    Explanations

    arithmetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    40
    -0.06
     wed
    -0.06
     diseño
    -0.06
     Ironically
    -0.06
    -ab
    -0.06
    09
    -0.06
    -existing
    -0.06
     Cbd
    -0.06
     �
    -0.06
    @end
    -0.06
    POSITIVE LOGITS
     filings
    0.06
    —and
    0.06
     Rails
    0.06
    uggle
    0.06
     hobby
    0.06
    用户
    0.06
     crossed
    0.06
    mpjes
    0.06
    ี
    0.06
     　　　　
    0.06
    Act Density 0.027%

    No Known Activations