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

    Neuronpedia

    INDEX
    Explanations

    so followed by comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     secretions
    1.49
    𝗵
    1.46
    靦
    1.38
    गोलिक
    1.33
    𝙖
    1.33
    ᴀ
    1.32
     striées
    1.30
    ﺎ
    1.28
    runtime
    1.27
    these
    1.27
    POSITIVE LOGITS
    ad
    1.43
    ின்
    1.22
    ati
    1.20
     de
    1.15
    вать
    1.15
     liệu
    1.15
     n
    1.11
    ak
    1.11
    oooo
    1.09
    uristic
    1.07
    Act Density 0.003%

    No Known Activations