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

    Neuronpedia

    INDEX
    Explanations

    argued

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izioni
    -0.07
     DN
    -0.07
     Mormon
    -0.07
     tabIndex
    -0.07
    赀
    -0.06
    inus
    -0.06
     `$
    -0.06
    ày
    -0.06
    token
    -0.06
    -cmpr
    -0.06
    POSITIVE LOGITS
     recre
    0.07
     Александр
    0.07
     fête
    0.07
    Playing
    0.07
    مشاريع
    0.06
     nestled
    0.06
    溲
    0.06
    ANDROID
    0.06
    Little
    0.06
     agréable
    0.06
    Act Density 0.002%

    No Known Activations