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

    Neuronpedia

    INDEX
    Explanations

    code or programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ANI
    -0.07
     locality
    -0.07
     KY
    -0.07
     nitrogen
    -0.07
    &e
    -0.07
    halten
    -0.06
    ชาย
    -0.06
    ounter
    -0.06
    TTY
    -0.06
    ربع
    -0.06
    POSITIVE LOGITS
     Navbar
    0.07
    .internet
    0.06
     LSTM
    0.06
    不
    0.06
    _destroy
    0.06
    .drop
    0.06
     )
↵
↵
    0.06
    (cuda
    0.06
     Help
    0.06
    ")!=
    0.06
    Act Density 0.061%

    No Known Activations