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

    Neuronpedia

    INDEX
    Explanations

    God, Krishna

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    入睡
    -0.07
    向社会
    -0.07
     UIPickerView
    -0.07
    $image
    -0.07
    came
    -0.07
    𝘌
    -0.07
    ㌢
    -0.07
    组成
    -0.07
    �
    -0.06
    _PAGES
    -0.06
    POSITIVE LOGITS
    Cla
    0.08
     Mountain
    0.08
    急忙
    0.08
    BERT
    0.07
     بدون
    0.07
    PGA
    0.07
    石化
    0.07
     PAL
    0.07
    台词
    0.07
    FORCE
    0.07
    Act Density 0.011%

    No Known Activations