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

    Neuronpedia

    INDEX
    Explanations

    filter

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .task
    -0.07
     merits
    -0.06
    COM
    -0.06
    USART
    -0.06
     yerinde
    -0.06
    _element
    -0.06
    com
    -0.05
    ばかり
    -0.05
     harvesting
    -0.05
    เหต
    -0.05
    POSITIVE LOGITS
     Bugs
    0.07
    öff
    0.07
    出
    0.07
     notified
    0.07
    ังกฤษ
    0.06
    :`
    0.06
    스코
    0.06
    財
    0.06
     编辑
    0.06
    fcn
    0.06
    Act Density 0.016%

    No Known Activations