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

    Neuronpedia

    INDEX
    Explanations

    technology/updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ex
    -1.50
     Ex
    -1.27
    Ex
    -1.23
    ex
    -1.23
     present
    -0.98
     update
    -0.96
    ux
    -0.88
    present
    -0.88
     Update
    -0.84
    update
    -0.83
    POSITIVE LOGITS
    eper
    0.59
    teps
    0.57
    ete
    0.56
     leitet
    0.56
    a
    0.53
    ubblica
    0.52
    stretchr
    0.52
    Demografía
    0.51
    zelfde
    0.51
     skydd
    0.50
    Act Density 0.065%

    No Known Activations