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

    Neuronpedia

    INDEX
    Explanations

    arising

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gal
    -0.08
    ,—
    -0.07
     CLEAN
    -0.07
     Tos
    -0.06
     Нав
    -0.06
     Markus
    -0.06
     Nou
    -0.06
    ��
    -0.06
    ела
    -0.06
    	Function
    -0.06
    POSITIVE LOGITS
    شف
    0.07
     �
    0.06
     upside
    0.06
    .recycle
    0.06
    .reducer
    0.06
    mm
    0.06
     dele
    0.06
    мин
    0.06
    UF
    0.06
    BackColor
    0.06
    Act Density 0.001%

    No Known Activations