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

    Neuronpedia

    INDEX
    Explanations

    inline code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻮ
    0.67
     Peña
    0.59
    U
    0.59
     Okay
    0.58
    _
    0.58
    O
    0.57
    D
    0.57
    UNESCO
    0.56
    UES
    0.55
    Sr
    0.55
    POSITIVE LOGITS
    ين
    0.86
    ↵
    0.79
    ции
    0.77
    ز
    0.68
     alguma
    0.66
     সরাসরি
    0.61
    ர
    0.61
     minimize
    0.61
    mé
    0.61
     közvet
    0.59
    Act Density 0.001%

    No Known Activations