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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dimensions
    -0.06
    imit
    -0.06
    And
    -0.06
     Wahl
    -0.06
    ongo
    -0.06
    imbus
    -0.06
    ookeeper
    -0.06
     böl
    -0.06
     Lub
    -0.05
    OH
    -0.05
    POSITIVE LOGITS
    	stats
    0.07
    	info
    0.07
     Vì
    0.07
    カード
    0.07
    奪
    0.07
    浮
    0.06
    Caught
    0.06
    usp
    0.06
     bench
    0.06
     sum
    0.06
    Act Density 0.014%

    No Known Activations