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

    Neuronpedia

    INDEX
    Explanations

    machine conscious

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ნ
    0.48
     shorter
    0.45
     theses
    0.45
    т
    0.45
     terus
    0.43
    ต่อ
    0.42
    τ
    0.42
    яд
    0.42
    更
    0.42
    த்தட்ட
    0.41
    POSITIVE LOGITS
    ​.
    0.46
     판매
    0.43
     کولو
    0.42
    ™.
    0.42
    ()){
    0.41
     považ
    0.41
    abe
    0.40
    kere
    0.40
     গণ্য
    0.40
     제품
    0.40
    Act Density 0.004%

    No Known Activations