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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     GA
    -0.07
     policym
    -0.07
     football
    -0.06
    NM
    -0.06
     họp
    -0.06
    乳业
    -0.06
     Mahm
    -0.06
    Datetime
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     hands
    0.08
    illed
    0.07
    ◅
    0.07
    竭
    0.07
    	want
    0.07
     immer
    0.07
    囿
    0.07
     (^)(
    0.07
    _PARAMETERS
    0.06
     WAY
    0.06
    Act Density 0.002%

    No Known Activations