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

    Neuronpedia

    INDEX
    Explanations

    command

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,pos
    -0.07
    過
    -0.07
    比
    -0.07
     Cha
    -0.07
     boosted
    -0.07
    	IN
    -0.06
    摇
    -0.06
    まず
    -0.06
     comparator
    -0.06
     Phot
    -0.06
    POSITIVE LOGITS
    НО
    0.07
    елефон
    0.07
     Authorization
    0.07
    ights
    0.06
     initialise
    0.06
    umed
    0.06
     nalez
    0.06
    (SK
    0.06
    ersen
    0.06
    upakan
    0.06
    Act Density 0.039%

    No Known Activations