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

    Neuronpedia

    INDEX
    Explanations

    found

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     PPC
    -0.07
    θέ
    -0.07
    .GetOrdinal
    -0.07
     Wants
    -0.06
    ♀
    -0.06
    356
    -0.06
    .getValueAt
    -0.06
     fanatic
    -0.06
    뿐
    -0.06
    POSITIVE LOGITS
    ’:
    0.08
    (load
    0.07
     relationships
    0.07
     pregn
    0.07
     evolved
    0.07
     consistently
    0.07
     rewarding
    0.06
     Palest
    0.06
     폴
    0.06
    /js
    0.06
    Act Density 0.028%

    No Known Activations