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

    Neuronpedia

    INDEX
    Explanations

    Encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    go
    -0.07
    _cre
    -0.07
    �
    -0.07
    伯
    -0.07
     rejo
    -0.07
    ／
    -0.06
    榱
    -0.06
     entidad
    -0.06
    positories
    -0.06
    彪
    -0.06
    POSITIVE LOGITS
    _EDIT
    0.07
    Disp
    0.07
    )').
    0.07
    热线
    0.07
     المر
    0.07
     noisy
    0.07
     boundary
    0.07
     LAT
    0.07
     ubiqu
    0.06
     Disp
    0.06
    Act Density 0.007%

    No Known Activations