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

    Neuronpedia

    INDEX
    Explanations

    els

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     captive
    -0.07
     huz
    -0.07
     Sky
    -0.06
     Flip
    -0.06
     arz
    -0.06
    /www
    -0.06
     Lei
    -0.06
     waar
    -0.06
    -game
    -0.06
     chores
    -0.06
    POSITIVE LOGITS
     forIndexPath
    0.11
     reuseIdentifier
    0.09
    .asList
    0.07
    getToken
    0.06
     Dro
    0.06
    Declare
    0.06
     бюджет
    0.06
    _backward
    0.06
     fileInfo
    0.06
    ")]
    0.06
    Act Density 0.000%

    No Known Activations