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

    Neuronpedia

    INDEX
    Explanations

    CSS font declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilt
    0.42
     prost
    0.39
     hex
    0.36
    机会
    0.36
     CLE
    0.35
    的机会
    0.35
    τη
    0.34
     energy
    0.34
    usto
    0.34
     digital
    0.34
    POSITIVE LOGITS
     déclar
    0.40
    ständ
    0.39
    скоп
    0.38
    بیل
    0.38
     источник
    0.38
    త్మ
    0.38
     бренда
    0.37
     جاتی
    0.37
    FileInputStream
    0.37
     déclare
    0.37
    Act Density 0.004%

    No Known Activations