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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wifi
    -0.07
     Sprite
    -0.07
     matrices
    -0.06
     市
    -0.06
     Slov
    -0.06
    	X
    -0.06
     PERSON
    -0.06
     이전
    -0.06
     trợ
    -0.06
    BigInteger
    -0.06
    POSITIVE LOGITS
     #@
    0.08
    :bold
    0.07
    codegen
    0.07
     khảo
    0.06
     annot
    0.06
     mostly
    0.06
    cosa
    0.06
    checked
    0.06
    _axes
    0.06
     بد
    0.06
    Act Density 0.001%

    No Known Activations