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

    Neuronpedia

    INDEX
    Explanations

    DDoS attacks, abandoned buildings, kids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     基于
    0.44
    ኦ
    0.43
     berdasarkan
    0.39
     comporte
    0.38
    负
    0.38
    դ
    0.37
     因
    0.37
    مل
    0.37
    PG
    0.37
    ח
    0.37
    POSITIVE LOGITS
     सगळ्या
    0.50
    喜び
    0.44
     😍
    0.43
    ጥነት
    0.43
    🤩
    0.43
    😍
    0.42
    💜
    0.41
     неви
    0.41
    💚
    0.40
    క్కి
    0.40
    Act Density 0.009%

    No Known Activations