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

    Neuronpedia

    INDEX
    Explanations

    avoiding influence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अक्सर
    0.47
     continent
    0.44
     যেখানে
    0.44
     destek
    0.44
     https
    0.43
     हमेशा
    0.43
     genellikle
    0.42
     ilk
    0.42
     tier
    0.41
     പിന്തുണ
    0.41
    POSITIVE LOGITS
    ریشن
    0.47
    нное
    0.41
    犹如
    0.40
    ційний
    0.39
    pH
    0.39
    sufficient
    0.39
     حقی
    0.38
    чого
    0.38
    OPHY
    0.38
    ност
    0.38
    Act Density 0.001%

    No Known Activations