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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    penup
    0.58
    ēl
    0.57
     করো
    0.57
    gx
    0.57
    gk
    0.56
    겅
    0.55
    DBOutput
    0.55
    GK
    0.55
    PerRow
    0.55
    奚
    0.55
    POSITIVE LOGITS
     if
    0.69
    Если
    0.61
     если
    0.60
    אם
    0.59
     agradable
    0.59
     совпада
    0.55
     якщо
    0.54
     اگه
    0.53
     நெ
    0.53
     emitting
    0.53
    Act Density 0.000%

    No Known Activations