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

    Neuronpedia

    INDEX
    Explanations

    zero values or absence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    າມ
    0.42
    刚刚
    0.42
    plane
    0.38
    uttle
    0.38
    afstand
    0.38
     आवृत्ति
    0.38
     कॉमन
    0.38
     protagonistas
    0.38
    rafl
    0.36
     ஆண
    0.36
    POSITIVE LOGITS
     blah
    0.46
     negligible
    0.46
     nonexistent
    0.41
    不存在
    0.41
     zero
    0.40
     ten
    0.39
     ND
    0.39
     xx
    0.39
    없
    0.38
     nil
    0.38
    Act Density 0.015%

    No Known Activations