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

    Neuronpedia

    INDEX
    Explanations

    a the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <data
    -0.08
     slij
    -0.08
    .onclick
    -0.08
    	kfree
    -0.08
     slots
    -0.08
    lež
    -0.08
     קט
    -0.07
     router
    -0.07
    	slot
    -0.07
     Parcelable
    -0.07
    POSITIVE LOGITS
     sterling
    0.08
    前年比
    0.08
     immaculate
    0.08
     మొత్త
    0.08
    全文
    0.08
     ఆమె
    0.08
     convex
    0.07
     Jens
    0.07
     проход
    0.07
    秀
    0.07
    Act Density 0.017%

    No Known Activations