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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itches
    -0.07
    _d
    -0.07
    hibited
    -0.07
    -ce
    -0.07
    lodash
    -0.06
    制度
    -0.06
     behaviors
    -0.06
    .Popup
    -0.06
     composing
    -0.06
    ʎ
    -0.06
    POSITIVE LOGITS
    顿
    0.08
     getStatus
    0.07
    ኢ
    0.07
    ły
    0.07
    𬱖
    0.06
     Initialization
    0.06
    宬
    0.06
    接听
    0.06
    孜
    0.06
     sł
    0.06
    Act Density 0.065%

    No Known Activations