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

    Neuronpedia

    INDEX
    Explanations

    vector

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shifts
    -0.07
     studying
    -0.07
     Scot
    -0.07
     Vine
    -0.07
    .transform
    -0.07
    aria
    -0.07
    werk
    -0.07
     Owen
    -0.07
    .Dataset
    -0.07
     cortical
    -0.07
    POSITIVE LOGITS
     tháng
    0.06
     Tôi
    0.06
     drowning
    0.06
     γρα
    0.06
    ılacak
    0.06
    parseFloat
    0.06
    ให
    0.05
    nable
    0.05
    '";↵
    0.05
     ANSI
    0.05
    Act Density 0.011%

    No Known Activations