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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    沈
    -0.07
     Holden
    -0.06
     Kend
    -0.06
     stabilized
    -0.06
    営
    -0.06
    редит
    -0.06
     Gdk
    -0.06
     XPAR
    -0.06
    _KEEP
    -0.06
     unpl
    -0.06
    POSITIVE LOGITS
     tür
    0.07
    others
    0.07
    ASURE
    0.07
    �
    0.06
     ทำ
    0.06
    ันท
    0.06
    еться
    0.06
    حه
    0.06
     chromosome
    0.06
    """
↵
↵
    0.06
    Act Density 0.003%

    No Known Activations