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

    Neuronpedia

    INDEX
    Explanations

    programming languages and technologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    `${
    0.38
    itel
    0.35
     sebagai
    0.35
     вместо
    0.35
    itton
    0.35
    合适的
    0.34
     মহাপ
    0.34
    ச்சியை
    0.34
    அந்த
    0.33
     najważ
    0.33
    POSITIVE LOGITS
     counterparts
    0.61
     counterpart
    0.55
     훨씬
    0.46
    지만
    0.39
    เพราะ
    0.38
     veya
    0.37
    훨
    0.37
     nhưng
    0.36
     ولكن
    0.36
     حتی
    0.36
    Act Density 0.188%

    No Known Activations