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

    Neuronpedia

    INDEX
    Explanations

    horizontal lines, code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NEY
    0.43
     equities
    0.42
     invest
    0.41
     agricult
    0.41
     assurances
    0.41
     prit
    0.41
     kinemat
    0.40
    ैंड
    0.40
     Jay
    0.40
     embank
    0.40
    POSITIVE LOGITS
    ارو
    0.41
     давно
    0.39
    ढ़
    0.38
    モチーフ
    0.38
     pasted
    0.38
    টক
    0.38
    ارت
    0.37
     ше
    0.37
     Пре
    0.37
    కి
    0.36
    Act Density 0.000%

    No Known Activations