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

    Neuronpedia

    INDEX
    Explanations

    seeing through or yourself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     аутох
    0.46
     می‌کند
    0.43
    ()=>{
    0.42
    utt
    0.38
     ジェ
    0.38
    става
    0.38
    oretically
    0.38
    orce
    0.37
     антен
    0.37
    рд
    0.37
    POSITIVE LOGITS
     clearly
    0.64
     jelas
    0.57
     👀
    0.56
     firsthand
    0.50
     fit
    0.49
     Clearly
    0.49
    Clearly
    0.47
    clearly
    0.46
     rõ
    0.45
    👀
    0.45
    Act Density 0.030%

    No Known Activations