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

    Neuronpedia

    INDEX
    Explanations

    no clear standard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erecht
    0.51
    tail
    0.50
    usch
    0.49
    ere
    0.46
    riu
    0.45
    los
    0.44
    riz
    0.44
    stdio
    0.44
    personality
    0.44
    rikes
    0.44
    POSITIVE LOGITS
    阿尔
    0.49
     abound
    0.48
     Either
    0.46
     att
    0.46
     он
    0.45
     aren
    0.44
     Tec
    0.43
     निभा
    0.43
     تت
    0.41
     determin
    0.41
    Act Density 0.002%

    No Known Activations