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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loading
    -0.07
     widget
    -0.07
     컴
    -0.07
     팀
    -0.07
     columnName
    -0.07
    .extensions
    -0.07
     frying
    -0.06
    dge
    -0.06
     publi
    -0.06
     LAND
    -0.06
    POSITIVE LOGITS
    kie
    0.07
    exit
    0.07
     discretion
    0.06
    َك
    0.06
    consider
    0.06
    sub
    0.06
    Certainly
    0.06
    ordination
    0.06
     Bath
    0.06
     Centro
    0.06
    Act Density 0.111%

    No Known Activations