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

    Neuronpedia

    INDEX
    Explanations

    description or details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    摫
    0.43
    憉
    0.42
    ędzynarod
    0.41
     giỏi
    0.41
    কেন্ড
    0.41
    䅡
    0.41
     പ്രസി
    0.40
     ആഘോഷ
    0.40
    जगी
    0.40
    斻
    0.40
    POSITIVE LOGITS
     rammed
    0.39
    rition
    0.38
     பாவ
    0.38
    ,.
    0.37
    ###
    0.36
     riser
    0.36
     ump
    0.35
    rapie
    0.34
    बू
    0.34
     lubric
    0.34
    Act Density 0.000%

    No Known Activations