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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	user
    -0.08
     field
    -0.07
     апреля
    -0.07
    $this
    -0.07
     lure
    -0.07
    布朗
    -0.07
    写下
    -0.06
     sint
    -0.06
     Estate
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     자유
    0.07
     sucess
    0.07
    _quality
    0.07
     Trial
    0.06
    饱
    0.06
     occult
    0.06
     inconvenient
    0.06
    添加剂
    0.06
    oding
    0.06
    ꩟
    0.06
    Act Density 0.001%

    No Known Activations