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

    Neuronpedia

    INDEX
    Explanations

    deals and inclusions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .orders
    -0.07
     Generator
    -0.07
    _Row
    -0.06
     debian
    -0.06
    _sex
    -0.06
    .Toolbar
    -0.06
    151
    -0.06
    undo
    -0.06
     neighborhood
    -0.06
     Purchase
    -0.06
    POSITIVE LOGITS
     expects
    0.06
     nominate
    0.06
     guaranteed
    0.06
    ('.');↵
    0.06
     ulong
    0.06
     jaké
    0.06
     '~/
    0.06
    -active
    0.06
    лю
    0.06
    連
    0.06
    Act Density 0.143%

    No Known Activations