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

    Neuronpedia

    INDEX
    Explanations

    structural markdown elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Über
    0.37
     Über
    0.35
    सीएल
    0.35
    UNG
    0.33
    держание
    0.33
    BESCHREIBUNG
    0.33
     zusammen
    0.32
    Gruß
    0.32
     splatter
    0.31
    __."
    0.31
    POSITIVE LOGITS
     nenhuma
    0.43
    None
    0.39
     None
    0.38
     berikut
    0.38
    none
    0.38
     nenhum
    0.38
    *
    0.37
    <table>
    0.37
     none
    0.34
    show
    0.34
    Act Density 0.000%

    No Known Activations