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

    Neuronpedia

    INDEX
    Explanations

    craft a descriptive thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     비슷
    0.51
     вси
    0.47
    有些人
    0.46
     vatth
    0.45
    핍
    0.44
     bunlar
    0.43
    ทำงาน
    0.43
     მთავ
    0.43
     仕事
    0.43
    <unused2008>
    0.43
    POSITIVE LOGITS
     የ
    0.56
     generic
    0.50
     E
    0.46
     customizable
    0.45
     Antarctic
    0.45
     flexible
    0.45
     Flexible
    0.43
     Australian
    0.43
     vintage
    0.43
     piezoelectric
    0.43
    Act Density 0.926%

    No Known Activations