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

    Neuronpedia

    INDEX
    Explanations

    especially, particularly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chars
    0.46
     Ph
    0.44
     f
    0.43
     Italian
    0.41
    化的
    0.41
     smallest
    0.40
     R
    0.40
     ប
    0.40
     Siemens
    0.40
    ten
    0.39
    POSITIVE LOGITS
    ,((
    0.49
    ,(((
    0.49
    蒇
    0.46
    鲛
    0.46
     aiuto
    0.44
     ಈಗಾಗಲೇ
    0.44
     أيض
    0.43
    覀
    0.43
     sowohl
    0.43
    还会
    0.42
    Act Density 0.006%

    No Known Activations