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

    Neuronpedia

    INDEX
    Explanations

    .fn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NO
    -0.07
     Telefon
    -0.07
     Monter
    -0.07
     neste
    -0.07
    咽
    -0.06
    鲧
    -0.06
     requestCode
    -0.06
    	struct
    -0.06
     rospy
    -0.06
     André
    -0.06
    POSITIVE LOGITS
    =[]↵
    0.08
    )
↵
    0.07
    }")↵
    0.07
    不停
    0.07
     hiding
    0.07
    ;")↵
    0.07
    олов
    0.07
    গ
    0.07
     ""),
    0.07
    髃
    0.07
    Act Density 0.002%

    No Known Activations