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

    Neuronpedia

    INDEX
    Explanations

    conditional statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getResult
    0.31
     any
    0.30
     [_
    0.30
    өлү
    0.29
     результата
    0.29
    ამო
    0.29
     результатов
    0.29
    <0x0D>
    0.28
    дук
    0.28
    лами
    0.28
    POSITIVE LOGITS
     일반적으로
    0.37
     イラスト
    0.35
     तिस
    0.34
     patru
    0.34
     dành
    0.33
     inwest
    0.33
     개최
    0.32
     jīn
    0.32
     그의
    0.32
     설계
    0.32
    Act Density 0.548%

    No Known Activations