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

    Neuronpedia

    INDEX
    Explanations

    states of being or process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    입니다
    0.56
    ဖြစ်သည်။
    0.51
    lerdir
    0.48
     입니다
    0.47
     ค่ะ
    0.47
     bulunmaktadır
    0.47
    ។
    0.46
     आहे
    0.46
     دارد
    0.45
     ஆவார்
    0.44
    POSITIVE LOGITS
    되는
    0.45
     olmayan
    0.45
    过程中
    0.42
    하지
    0.41
     시간에는
    0.40
    のない
    0.40
    되면
    0.40
     없는
    0.40
    രിക്കുന്ന
    0.40
    하는
    0.39
    Act Density 0.009%

    No Known Activations