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

    Neuronpedia

    INDEX
    Explanations

    Antioxidants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    確認
    -0.07
     human
    -0.06
    _REASON
    -0.06
     hanya
    -0.06
    _ANAL
    -0.06
    itary
    -0.06
     khuyến
    -0.06
    -pin
    -0.06
    _curr
    -0.06
    /path
    -0.06
    POSITIVE LOGITS
     son
    0.07
     leader
    0.06
     sails
    0.06
    .grey
    0.06
     chopping
    0.06
     Lucia
    0.06
     Settings
    0.06
     Vertical
    0.06
     matlab
    0.06
     Serif
    0.06
    Act Density 0.051%

    No Known Activations