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

    Neuronpedia

    INDEX
    Explanations

    compounding and growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Convergence
    0.44
    道
    0.40
     பட்
    0.38
    Ę
    0.38
     Length
    0.37
    Repost
    0.37
     متش
    0.36
    CD
    0.36
     Examples
    0.36
     CAUSED
    0.36
    POSITIVE LOGITS
    meni
    0.45
    anii
    0.45
    ნიშვნ
    0.44
    ieni
    0.41
    кому
    0.41
     bathe
    0.41
     المبلغ
    0.39
     antique
    0.39
    उचर
    0.39
     inadequacy
    0.39
    Act Density 0.000%

    No Known Activations