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

    Neuronpedia

    INDEX
    Explanations

    empty lists `[]`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يام
    0.38
     riego
    0.38
     mejorar
    0.34
     trava
    0.34
     trova
    0.34
     pide
    0.34
     förb
    0.34
     hö
    0.34
     wybr
    0.34
     finne
    0.34
    POSITIVE LOGITS
    empty
    0.44
    空
    0.38
    Empty
    0.37
    Array
    0.36
    max
    0.36
    磁盘
    0.36
    包含
    0.36
    将
    0.35
    EMPTY
    0.35
     ರಚ
    0.34
    Act Density 0.200%

    No Known Activations