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

    Neuronpedia

    INDEX
    Explanations

    list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     öffentlich
    0.41
    认真
    0.41
     তাঁদের
    0.39
    谨慎
    0.38
     তাঁরা
    0.38
     offent
    0.37
    Trad
    0.36
     ඔවුන්
    0.36
    芊
    0.36
    ࿐
    0.35
    POSITIVE LOGITS
    :
    0.56
     entropy
    0.54
    ：
    0.50
    以下の
    0.48
     divisors
    0.48
     complicates
    0.48
     reducing
    0.46
     mism
    0.46
    ﹕
    0.46
     situations
    0.46
    Act Density 0.047%

    No Known Activations