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

    Neuronpedia

    INDEX
    Explanations

    conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tall
    -0.08
    不曾
    -0.07
    Slide
    -0.07
    ==>
    -0.07
     Particularly
    -0.07
    <H
    -0.07
     fig
    -0.07
     Knot
    -0.07
    測
    -0.07
     stump
    -0.07
    POSITIVE LOGITS
     recursive
    0.08
    aron
    0.07
    婢
    0.07
    彼ら
    0.07
    عامل
    0.07
    ard
    0.06
    딤
    0.06
     stylist
    0.06
    �
    0.06
    女儿
    0.06
    Act Density 0.113%

    No Known Activations