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

    Neuronpedia

    INDEX
    Explanations

    Unusual characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Silk
    -0.07
     Exhibition
    -0.06
     Chef
    -0.06
    Blue
    -0.06
    lder
    -0.06
     development
    -0.06
    ıklı
    -0.06
     hjem
    -0.06
     Each
    -0.06
     providing
    -0.06
    POSITIVE LOGITS
    终点
    0.07
    歷史
    0.07
    ☿
    0.07
    芫
    0.07
    鬧
    0.07
     Mn
    0.07
     sne
    0.07
    Intl
    0.07
     Verg
    0.06
     =================================================================================
    0.06
    Act Density 0.007%

    No Known Activations