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
    shit
    -0.08
    раста
    -0.07
    _ANGLE
    -0.07
     fantas
    -0.07
     maze
    -0.06
    ROUTE
    -0.06
     SHIFT
    -0.06
     CentOS
    -0.06
    _SH
    -0.06
     Scarborough
    -0.06
    POSITIVE LOGITS
    、《
    0.07
    薄
    0.06
    』↵↵
    0.06
    useState
    0.06
    )_
    0.06
     debunk
    0.06
    _/
    0.06
    �
    0.06
     komunik
    0.06
     accessor
    0.06
    Act Density 0.002%

    No Known Activations