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

    Neuronpedia

    INDEX
    Explanations

    orne

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    typename
    -0.07
    AndView
    -0.06
     mujer
    -0.06
    ίγ
    -0.06
     vivid
    -0.06
     Aly
    -0.06
    assign
    -0.06
    venues
    -0.06
     himself
    -0.06
     Commons
    -0.06
    POSITIVE LOGITS
    加
    0.07
    検
    0.07
     widget
    0.07
    �
    0.07
    	Action
    0.07
    !↵
    0.06
     ARGS
    0.06
     Shape
    0.06
    ?key
    0.06
    )])↵
    0.06
    Act Density 0.000%

    No Known Activations