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

    Neuronpedia

    INDEX
    Explanations

    ellipses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AutoSize
    -0.08
    '",
    -0.08
     admired
    -0.07
    _batches
    -0.07
    .parsers
    -0.07
     England
    -0.07
     所
    -0.07
    ighbor
    -0.07
     Ricardo
    -0.07
    اى
    -0.07
    POSITIVE LOGITS
    LOUD
    0.07
     IND
    0.07
     …↵
    0.06
     Presented
    0.06
     almond
    0.06
    sleep
    0.06
    यन
    0.06
    (ctrl
    0.06
     движ
    0.06
    ındır
    0.06
    Act Density 0.019%

    No Known Activations