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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .forChild
    -0.07
     afore
    -0.07
     phiếu
    -0.06
    ಛ
    -0.06
    endid
    -0.06
    Full
    -0.06
     çocuğu
    -0.06
     Sold
    -0.06
    YOU
    -0.06
    olve
    -0.06
    POSITIVE LOGITS
     Bản
    0.08
    委员
    0.07
    -speaking
    0.07
    的时间
    0.07
     criticizing
    0.07
    每日经济
    0.07
     wrench
    0.07
    wać
    0.07
    可以说
    0.07
    houette
    0.07
    Act Density 0.001%

    No Known Activations