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

    Neuronpedia

    INDEX
    Explanations

    return (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    介護
    0.79
     فیصل
    0.77
    茂
    0.75
     {{-
    0.73
    {{
    0.72
    ={$
    0.70
    Roxy
    0.70
    ποί
    0.69
    ={{
    0.69
    Demand
    0.69
    POSITIVE LOGITS
     <>
    1.22
    <>
    1.15
     <
    0.84
    path
    0.82
    obs
    0.81
     (<
    0.78
    ＜
    0.71
     tł
    0.70
    <div>
    0.70
     ＜
    0.70
    Act Density 0.028%

    No Known Activations