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

    Neuronpedia

    INDEX
    Explanations

    most compact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bookmark
    0.42
    ės
    0.41
    adaşlar
    0.41
    वाड़ा
    0.41
     –
    0.40
    alı
    0.40
    zelf
    0.40
     أس
    0.40
    さて
    0.40
    <h2>
    0.39
    POSITIVE LOGITS
    CLUDES
    0.46
    QUANT
    0.43
     করেন
    0.42
    attoos
    0.41
    সংখ্যক
    0.41
     manifestly
    0.41
    σκεται
    0.40
    HISTORY
    0.38
     Woolf
    0.38
     характеризу
    0.38
    Act Density 0.000%

    No Known Activations