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
     Neighborhood
    -0.07
    Ster
    -0.07
     Acceler
    -0.07
    som
    -0.07
     telescope
    -0.07
     toe
    -0.06
    牢固树立
    -0.06
     Pediatric
    -0.06
    lov
    -0.06
    studio
    -0.06
    POSITIVE LOGITS
    FULL
    0.07
    PLUGIN
    0.07
    DDL
    0.07
    ???
    0.07
    我才
    0.07
    /path
    0.07
    	throws
    0.07
    _patterns
    0.07
    _DAYS
    0.07
    大纲
    0.06
    Act Density 0.029%

    No Known Activations