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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (widget
    -0.07
     prefab
    -0.06
    图
    -0.06
    setIcon
    -0.06
    ember
    -0.06
     파일첨부
    -0.06
     Heavy
    -0.06
    meta
    -0.06
    Parcel
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     when
    0.06
     ctl
    0.06
     los
    0.06
    Represent
    0.06
    pear
    0.06
     Shen
    0.06
    	elif
    0.06
    165
    0.06
     игра
    0.06
     elif
    0.06
    Act Density 0.033%

    No Known Activations