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

    Neuronpedia

    INDEX
    Explanations

    It's just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     definitely
    0.41
     definitiv
    0.41
     sezonie
    0.41
    ക്കൊ
    0.40
     season
    0.39
    絟
    0.39
     almost
    0.38
    渫
    0.38
     संरक्षण
    0.38
    !»
    0.38
    POSITIVE LOGITS
     различными
    0.40
     различные
    0.38
    および
    0.38
    Okay
    0.38
     okay
    0.38
     괜찮
    0.38
     ملاقات
    0.37
    ノ
    0.37
     Okay
    0.36
    ﻳ
    0.36
    Act Density 0.015%

    No Known Activations