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

    Neuronpedia

    INDEX
    Explanations

    Characters related to other characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wolff
    -0.07
     updateUser
    -0.07
     Juni
    -0.07
     ATA
    -0.06
    ecure
    -0.06
     tokenId
    -0.06
     occur
    -0.06
    ubernetes
    -0.06
    (game
    -0.06
     IMO
    -0.06
    POSITIVE LOGITS
    .txt
    0.06
     "(
    0.06
    .H
    0.06
    HH
    0.06
     клі
    0.06
     fitting
    0.06
    .about
    0.06
     meiden
    0.06
    :not
    0.06
    ees
    0.06
    Act Density 0.120%

    No Known Activations