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

    Neuronpedia

    INDEX
    Explanations

    okay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    心的
    0.40
     Gul
    0.40
     kel
    0.39
    给出
    0.39
    atas
    0.39
     આપે
    0.38
     elimina
    0.38
    kel
    0.38
     hacerlo
    0.38
    azos
    0.38
    POSITIVE LOGITS
     lze
    0.44
     içeren
    0.42
     supervising
    0.41
    ୬
    0.39
    ŧ
    0.39
    ᅣ
    0.39
    り
    0.38
    ｐ
    0.38
     considerado
    0.37
     рассматривать
    0.37
    Act Density 0.002%

    No Known Activations