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

    Neuronpedia

    INDEX
    Explanations

    uff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Göz
    -0.07
     spectra
    -0.06
            
↵
    -0.06
     rhythm
    -0.06
    root
    -0.06
    Erot
    -0.06
    Bio
    -0.06
    クリ
    -0.06
     proc
    -0.06
    Nonnull
    -0.06
    POSITIVE LOGITS
     Huff
    0.07
    UFF
    0.07
    TES
    0.07
    uff
    0.07
    �
    0.07
    IFS
    0.07
    ussia
    0.06
    слов
    0.06
     appel
    0.06
    urret
    0.06
    Act Density 0.016%

    No Known Activations