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

    Neuronpedia

    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ни
    -0.07
    🤑
    -0.06
    孩子们
    -0.06
    pps
    -0.06
     Prince
    -0.06
    잼
    -0.06
     자신의
    -0.06
    .Imp
    -0.06
    .Prop
    -0.06
    "display
    -0.06
    POSITIVE LOGITS
    豐
    0.07
    镗
    0.07
    _dc
    0.07
     hsv
    0.06
    _NC
    0.06
    kb
    0.06
    adores
    0.06
     dieta
    0.06
     largo
    0.06
    差异
    0.06
    Act Density 0.020%

    No Known Activations