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

    Neuronpedia

    INDEX
    Explanations

    algorithmic, potentially, clean, revenue, evolving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enthusiastic
    0.49
    inya
    0.49
     great
    0.48
     genial
    0.48
    ፣
    0.47
     keen
    0.47
    Motor
    0.46
    Mét
    0.46
     legendary
    0.45
     काय
    0.45
    POSITIVE LOGITS
    加えて
    0.52
    സ്ഥ
    0.47
    书
    0.46
    减
    0.46
    ட்சய
    0.46
    更
    0.46
    家
    0.46
    푞
    0.45
    酈
    0.45
     phù
    0.45
    Act Density 0.000%

    No Known Activations