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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ener
    -0.07
    配有
    -0.07
     Hale
    -0.07
     apro
    -0.07
    ';
↵
↵
    -0.06
     Dias
    -0.06
    >).
    -0.06
    PAL
    -0.06
    ี
    -0.06
    (coord
    -0.06
    POSITIVE LOGITS
    .Parcelable
    0.08
    Genre
    0.07
    주의
    0.07
    ランド
    0.06
     jewel
    0.06
     UserID
    0.06
    數據
    0.06
     reliably
    0.06
    硅
    0.06
    ទ
    0.06
    Act Density 0.066%

    No Known Activations