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

    Neuronpedia

    INDEX
    Explanations

    python script main execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kệ
    0.66
     entwick
    0.63
     EDF
    0.63
     pyram
    0.61
     aufge
    0.61
     lift
    0.60
    ждается
    0.60
     EDP
    0.60
     Yarm
    0.60
     Doss
    0.60
    POSITIVE LOGITS
    __":
    0.80
    റ്റ്‌
    0.61
     Том
    0.57
    }}_{\
    0.57
     ঔষধ
    0.56
    uts
    0.56
    atz
    0.55
     অসু
    0.55
    𝗰
    0.54
     опытом
    0.54
    Act Density 0.059%

    No Known Activations