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

    Neuronpedia

    INDEX
    Explanations

    references and notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     actionMode
    0.43
     ঘন
    0.41
     அதிகரிக்கிறது
    0.41
     Oldborough
    0.40
     பாதிக்கிறது
    0.39
    ὺ
    0.38
    ర్వాత
    0.38
    )：
    0.38
     বাঁচাতে
    0.38
     создавать
    0.37
    POSITIVE LOGITS
     whims
    0.48
    www
    0.48
    refer
    0.47
    Referensi
    0.47
    References
    0.46
    Referencias
    0.46
    reference
    0.44
    references
    0.43
    Referències
    0.42
    cite
    0.42
    Act Density 0.000%

    No Known Activations