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

    Neuronpedia

    INDEX
    Explanations

    automatic yes confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tuned
    0.39
     Mull
    0.39
     Seller
    0.38
     Lent
    0.38
     lent
    0.38
     jewel
    0.37
     Energy
    0.36
     Jewel
    0.36
     كيفية
    0.36
     pí
    0.36
    POSITIVE LOGITS
     upgrade
    0.42
    upgrade
    0.41
     निवड
    0.41
     Приступ
    0.41
    நாயக
    0.39
    útbol
    0.39
     upgrading
    0.38
    TION
    0.38
    қу
    0.38
    qq
    0.38
    Act Density 0.015%

    No Known Activations