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

    Neuronpedia

    INDEX
    Explanations

    Common sentence words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    init
    -0.06
    ElementException
    -0.06
     Laurel
    -0.06
    068
    -0.06
     Copa
    -0.06
    "G
    -0.06
    chunk
    -0.06
    "F
    -0.05
     Cosby
    -0.05
    鎮
    -0.05
    POSITIVE LOGITS
    _remove
    0.07
     measuring
    0.07
     examination
    0.07
     LOOK
    0.07
     art
    0.07
       
    0.07
     institutions
    0.07
    unic
    0.06
     bloc
    0.06
     </>↵
    0.06
    Act Density 0.000%

    No Known Activations