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

    Neuronpedia

    INDEX
    Explanations

    MAX

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    基本
    -0.07
     cultural
    -0.07
    iter
    -0.07
     auditing
    -0.06
     เด
    -0.06
     inmates
    -0.06
    ites
    -0.06
    .getName
    -0.06
    kur
    -0.06
     dashes
    -0.06
    POSITIVE LOGITS
     розрах
    0.07
    .Enabled
    0.07
     exc
    0.06
     Mặt
    0.06
     achter
    0.06
    ='#
    0.06
    each
    0.06
     ample
    0.06
     &[
    0.06
    icycle
    0.06
    Act Density 0.016%

    No Known Activations