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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Transport
    -0.07
    .downcase
    -0.07
     Brewers
    -0.07
    prime
    -0.07
     Science
    -0.07
     phenotype
    -0.07
    Stuff
    -0.07
     Floor
    -0.06
    _record
    -0.06
     Gun
    -0.06
    POSITIVE LOGITS
    双边
    0.07
    率达
    0.07
    xito
    0.07
     많은
    0.07
    脸颊
    0.07
     seeks
    0.07
    すぎる
    0.07
     seit
    0.06
    راك
    0.06
    forg
    0.06
    Act Density 0.128%

    No Known Activations