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

    Neuronpedia

    INDEX
    Explanations

    numbers and non-Latin scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rumah
    0.45
     Reykjav
    0.42
     reunión
    0.41
     چهار
    0.40
     rumah
    0.40
     जरिये
    0.40
    昛
    0.39
    bbR
    0.39
    гии
    0.39
     要
    0.39
    POSITIVE LOGITS
    による
    0.46
    6
    0.44
    <0xB2>
    0.39
     ۱۵
    0.39
     કેરી
    0.38
    ต้อง
    0.37
     sixteenth
    0.37
    5
    0.36
    ၆
    0.36
    minist
    0.35
    Act Density 0.125%

    No Known Activations