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

    Neuronpedia

    INDEX
    Explanations

    describes negative actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ক্যাথোডে
    0.46
    id
    0.42
    ³
    0.42
    міна
    0.41
    бычно
    0.41
    манов
    0.40
    Servers
    0.40
    ման
    0.39
    RGB
    0.39
    ემ
    0.39
    POSITIVE LOGITS
     Beide
    0.55
     Diese
    0.46
    imsu
    0.45
    ابق
    0.45
    大きい
    0.44
     teie
    0.42
     beide
    0.42
     सारी
    0.42
     demikian
    0.42
     Kleid
    0.41
    Act Density 0.001%

    No Known Activations