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

    Neuronpedia

    INDEX
    Explanations

    normal maps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ८
    0.44
    ினான்
    0.41
    𝘾
    0.41
    0.41
     compreensão
    0.39
    八
    0.39
    ฉัน
    0.38
    Fif
    0.38
     คลิก
    0.38
    corollary
    0.37
    POSITIVE LOGITS
    7
    0.40
    |
    0.40
    ’
    0.38
    (*)
    0.37
    <0xB3>
    0.37
     Accident
    0.36
     স্বাস্থ্য
    0.36
    5
    0.36
    এক
    0.35
     His
    0.35
    Act Density 0.035%

    No Known Activations