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

    Neuronpedia

    INDEX
    Explanations

    review

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sao
    -0.07
     faithfully
    -0.07
     suk
    -0.07
     scrolling
    -0.07
    �다
    -0.06
    üre
    -0.06
    支付
    -0.06
     Alignment
    -0.06
    楼
    -0.06
    reetings
    -0.06
    POSITIVE LOGITS
     review
    0.06
    _mobile
    0.06
    .withOpacity
    0.06
     holland
    0.06
    _Style
    0.06
     quân
    0.06
    usuarios
    0.06
     없이
    0.06
    783
    0.06
    Paper
    0.06
    Act Density 0.006%

    No Known Activations