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

    Neuronpedia

    INDEX
    Explanations

    programming, relationship, poverty, medical conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ದ
    0.27
    க்க
    0.25
     uterine
    0.25
    かない
    0.25
    kuu
    0.25
     glorie
    0.24
     Lush
    0.24
    ば
    0.24
     Deine
    0.24
    Mega
    0.24
    POSITIVE LOGITS
     কপ
    0.28
    ‘
    0.27
    LEV
    0.25
     ὁ
    0.25
     “(
    0.25
     acquist
    0.25
     Въ
    0.24
     방법에
    0.24
    랜
    0.24
    ونها
    0.23
    Act Density 0.330%

    No Known Activations