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

    Neuronpedia

    INDEX
    Explanations

    My

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recommended
    0.46
     based
    0.45
    ᱴ
    0.44
     hoped
    0.43
    commended
    0.42
     Consultant
    0.41
     Tracker
    0.41
    underline
    0.41
    veer
    0.41
     prefers
    0.41
    POSITIVE LOGITS
     кре
    0.50
     зако
    0.43
     cré
    0.41
    けると
    0.40
    けます
    0.39
    ätzen
    0.38
     ziemlich
    0.38
     listopada
    0.38
     тексти
    0.38
     entrambe
    0.37
    Act Density 0.132%

    No Known Activations