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

    Neuronpedia

    INDEX
    Explanations

    modeling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Group
    -0.07
    ').
    -0.06
    Lng
    -0.06
    ”).
    -0.06
    ").
    -0.06
     cit
    -0.06
     incel
    -0.06
    Qui
    -0.06
    Aliases
    -0.06
    丈夫
    -0.06
    POSITIVE LOGITS
     EIF
    0.07
    ][_
    0.07
     conceive
    0.06
    .IOException
    0.06
    연
    0.06
     Brittany
    0.06
    	TokenName
    0.06
    вана
    0.06
    ؤول
    0.06
     Sheridan
    0.06
    Act Density 0.117%

    No Known Activations