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

    Neuronpedia

    INDEX
    Explanations

    Code and models

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Played
    -0.08
    Read
    -0.07
     dece
    -0.07
     theater
    -0.06
     drowned
    -0.06
    Wide
    -0.06
    Hope
    -0.06
    uku
    -0.06
    American
    -0.06
     helpers
    -0.06
    POSITIVE LOGITS
     Americas
    0.07
     Emperor
    0.07
     Blur
    0.07
    uplicates
    0.07
    委員
    0.07
    _TRNS
    0.07
    PrimaryKey
    0.06
    .OrdinalIgnoreCase
    0.06
    (coeff
    0.06
     UIImagePickerController
    0.06
    Act Density 0.035%

    No Known Activations