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

    Neuronpedia

    INDEX
    Explanations

    Bas

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mería
    0.66
     डाय
    0.63
    ona
    0.62
    وزيع
    0.62
    দুল
    0.62
     மோச
    0.62
     Изда
    0.61
    ued
    0.60
     لن
    0.60
     Eigent
    0.58
    POSITIVE LOGITS
     ER
    0.74
    িয়াই
    0.70
     Kiv
    0.69
     দিলাম
    0.69
     matou
    0.69
     వరు
    0.68
     акаде
    0.68
     glLightfv
    0.67
     academy
    0.63
     মিঃ
    0.63
    Act Density 0.002%

    No Known Activations