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

    Neuronpedia

    INDEX
    Explanations

    words that have to do with food, cooking or restaurants

    oai_token-act-pair · gemini-2.0-flash

    bread

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lebo
    -0.53
    rest
    -0.49
    reusable
    -0.49
    Mip
    -0.48
    Greet
    -0.48
    ladu
    -0.47
    améli
    -0.45
    ప
    -0.45
    ousine
    -0.45
    Bode
    -0.45
    POSITIVE LOGITS
    drawSprites
    0.56
    setLayoutManager
    0.56
     متعلقه
    0.54
    HasForeignKey
    0.52
    UniformLocation
    0.51
    ukone
    0.51
    tableFuture
    0.50
    \{\\
    0.50
     **)
    0.49
    SPATH
    0.49
    Act Density 1.983%

    No Known Activations