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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .groups
    -0.07
    飏
    -0.07
    executor
    -0.07
    ",__
    -0.07
    .theta
    -0.07
    �
    -0.07
    儇
    -0.06
     radiator
    -0.06
    浦
    -0.06
    	Main
    -0.06
    POSITIVE LOGITS
    胆固醇
    0.07
     LEG
    0.07
    ences
    0.07
     //
↵
↵
    0.06
    핞
    0.06
     Ceiling
    0.06
    ------↵↵
    0.06
    获得了
    0.06
     Köln
    0.06
    Billing
    0.06
    Act Density 0.003%

    No Known Activations