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

    Neuronpedia

    INDEX
    Explanations

    consequences and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    虜
    0.48
    worldwide
    0.47
     букмекерлер
    0.45
    年の
    0.44
     йөк
    0.42
     психи
    0.42
     ма
    0.42
     पत्रिका
    0.42
     научно
    0.42
    年から
    0.42
    POSITIVE LOGITS
     suav
    0.46
    时
    0.45
    فير
    0.43
     suaves
    0.43
     seul
    0.43
    etr
    0.42
    erkt
    0.42
    aneous
    0.42
     inverses
    0.42
    aniu
    0.41
    Act Density 0.003%

    No Known Activations