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

    Neuronpedia

    INDEX
    Explanations

    Possessive contractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     разви
    -0.07
     disdain
    -0.06
     مور
    -0.06
    =log
    -0.06
     Stand
    -0.06
     випад
    -0.06
     watchers
    -0.06
     Glam
    -0.06
     simpl
    -0.06
     바로
    -0.06
    POSITIVE LOGITS
    .setOn
    0.07
    rose
    0.07
    `()
    0.07
     caramel
    0.06
    :!
    0.06
     extras
    0.06
    ）↵
    0.06
     brewing
    0.06
     rainy
    0.06
    char
    0.06
    Act Density 0.007%

    No Known Activations