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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     certify
    -0.07
    นอ
    -0.06
     trades
    -0.06
     fight
    -0.06
     γρα
    -0.06
    .Debugf
    -0.06
    .…↵↵
    -0.06
    、お
    -0.06
    SelectedItem
    -0.06
    .`);↵
    -0.06
    POSITIVE LOGITS
    rate
    0.07
     voucher
    0.06
    	last
    0.06
    在地
    0.06
     Vaccine
    0.06
    [G
    0.06
    -await
    0.06
     inexp
    0.06
     affine
    0.06
     الكه
    0.06
    Act Density 0.015%

    No Known Activations