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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _prepare
    -0.07
    WidthSpace
    -0.06
     Thy
    -0.06
    unicode
    -0.06
    ायत
    -0.06
    й
    -0.06
     wys
    -0.06
    нение
    -0.06
     Vari
    -0.06
    ET
    -0.06
    POSITIVE LOGITS
     DECL
    0.07
    [iVar
    0.07
     Ä
    0.07
    =g
    0.07
     disag
    0.07
    _HANDLE
    0.06
     Khoa
    0.06
     德
    0.06
     socioeconomic
    0.06
     ^{°}
    0.06
    Act Density 0.104%

    No Known Activations