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

    Neuronpedia

    INDEX
    Explanations

    Code packages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    墙壁
    -0.08
    け
    -0.06
    git
    -0.06
     reverse
    -0.06
    ッチ
    -0.06
    caffe
    -0.06
     MAR
    -0.06
    	addr
    -0.06
    精髓
    -0.06
     Marr
    -0.06
    POSITIVE LOGITS
     ();
↵
    0.07
    Chooser
    0.07
     ();
    0.07
    Adjusted
    0.07
    镩
    0.07
     NSK
    0.07
    chrom
    0.07
    峧
    0.07
    UIL
    0.07
     ----------------------------------------------------------------------------------------------------------------
    0.06
    Act Density 0.001%

    No Known Activations