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

    Neuronpedia

    INDEX
    Explanations

    DP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DP
    -0.75
     sumpay
    -0.67
    chtete
    -0.66
     Cornish
    -0.64
     TPR
    -0.63
    ussis
    -0.63
     DP
    -0.61
     femininas
    -0.61
     pouvoit
    -0.60
     peuples
    -0.60
    POSITIVE LOGITS
    veras
    0.52
     sin
    0.50
    formik
    0.49
     sea
    0.49
    awtextra
    0.48
    fum
    0.47
    WriteTagHelper
    0.47
     din
    0.45
    Autoritní
    0.45
     barat
    0.45
    Act Density 0.095%

    No Known Activations