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

    Neuronpedia

    INDEX
    Explanations

    numbers 6 following 8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     faces
    0.38
     takers
    0.38
     процен
    0.38
     plead
    0.37
     exited
    0.37
    hund
    0.37
     варі
    0.36
     pro
    0.36
     says
    0.36
    kyo
    0.36
    POSITIVE LOGITS
     প্রেসিডেন্টের
    0.39
     centro
    0.39
     Enable
    0.39
    偶
    0.38
    льне
    0.38
     Leach
    0.38
     Upon
    0.37
    䉍
    0.37
    伖
    0.37
     Traffic
    0.36
    Act Density 0.000%

    No Known Activations