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

    Neuronpedia

    INDEX
    Explanations

    analogy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    তত্ব
    0.49
     shinobi
    0.48
     patt
    0.47
    gif
    0.46
     marinade
    0.46
    quillo
    0.46
    ley
    0.46
     patina
    0.46
    mission
    0.46
     fondant
    0.46
    POSITIVE LOGITS
    ب
    0.62
    ৫
    0.52
    这两个
    0.50
    આ
    0.48
    இ
    0.48
    يع
    0.48
    这两
    0.47
     واحدة
    0.47
    无论是
    0.47
     undergraduates
    0.46
    Act Density 0.000%

    No Known Activations