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

    Neuronpedia

    INDEX
    Explanations

    Language/translation passages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MMM
    -0.07
    خان
    -0.07
    받
    -0.07
    qq
    -0.07
     Ik
    -0.06
    Ds
    -0.06
    กว
    -0.06
    ยะ
    -0.06
    站
    -0.06
    fea
    -0.06
    POSITIVE LOGITS
     biod
    0.07
     proves
    0.06
    гов
    0.06
    =create
    0.06
    ARSER
    0.06
     cerca
    0.06
     Feeling
    0.06
     Sexual
    0.06
     COMMON
    0.06
     monitoring
    0.06
    Act Density 0.093%

    No Known Activations