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

    Neuronpedia

    INDEX
    Explanations

    list items with bullet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     phosphoryl
    0.28
    indexOf
    0.26
    tosecond
    0.25
    |$,
    0.25
    မဲ့
    0.24
     ওজন
    0.24
    কেই
    0.24
     названия
    0.24
    ύ
    0.24
    腌
    0.24
    POSITIVE LOGITS
    </h3>
    0.29
    ۔
    0.25
     standout
    0.24
     কিন্ত
    0.23
     fear
    0.23
     সবচে
    0.23
     yoki
    0.23
    𒐪
    0.23
     を
    0.22
    punkt
    0.22
    Act Density 0.146%

    No Known Activations