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

    Neuronpedia

    INDEX
    Explanations

    driven humanity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ademia
    0.50
    ᱕
    0.48
    ᱖
    0.46
    ї
    0.45
     occurring
    0.45
     Сто
    0.44
    ᱗
    0.44
     centred
    0.42
    бор
    0.42
     apabila
    0.42
    POSITIVE LOGITS
    م
    0.55
    小說
    0.52
     تصميم
    0.45
    энне
    0.45
     origen
    0.45
     lå
    0.45
    يان
    0.44
    ioribus
    0.44
    獠
    0.44
    里昂
    0.44
    Act Density 0.001%

    No Known Activations