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

    Neuronpedia

    INDEX
    Explanations

    rate following at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dara
    0.46
     معلوم
    0.37
    ዻ
    0.35
    feld
    0.34
    èng
    0.34
     سیم
    0.34
    modations
    0.34
     authorizations
    0.33
    浃
    0.33
     যুগে
    0.33
    POSITIVE LOGITS
     auquel
    0.98
     at
    0.93
     auxquelles
    0.80
     auxquels
    0.78
     waarop
    0.74
     వద్ద
    0.67
    At
    0.66
     At
    0.62
     atthe
    0.62
     tại
    0.61
    Act Density 0.021%

    No Known Activations