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

    Neuronpedia

    INDEX
    Explanations

    personal anecdotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Skipping
    -0.06
    $config
    -0.06
    banner
    -0.06
    <!--[
    -0.06
     Becker
    -0.06
     funcs
    -0.06
     الی
    -0.05
     návr
    -0.05
     Glock
    -0.05
    远
    -0.05
    POSITIVE LOGITS
    (and
    0.07
    (avg
    0.07
    řeh
    0.07
    well
    0.07
    _open
    0.07
    each
    0.07
    ↵↵↵
    0.07
     Abyss
    0.06
    ucceeded
    0.06
    ै।↵
    0.06
    Act Density 0.087%

    No Known Activations