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

    Neuronpedia

    INDEX
    Explanations

    et

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    坋
    -0.07
    commercial
    -0.07
    쌓
    -0.06
    =text
    -0.06
     //================================================================
    -0.06
    复杂的
    -0.06
    addChild
    -0.06
    ульт
    -0.06
    𝕍
    -0.06
    	opt
    -0.06
    POSITIVE LOGITS
    bron
    0.07
     FULL
    0.07
    commended
    0.07
    LOTS
    0.06
    guards
    0.06
    الجز
    0.06
     reliability
    0.06
    舰队
    0.06
    _free
    0.06
    _DENIED
    0.06
    Act Density 0.001%

    No Known Activations