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

    Neuronpedia

    INDEX
    Explanations

    specifying alternatives or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    πό
    0.54
    icules
    0.48
    urai
    0.47
    šku
    0.47
    culas
    0.46
    ورٹی
    0.45
    ună
    0.45
    hitva
    0.45
    igrants
    0.45
    hid
    0.44
    POSITIVE LOGITS
     Hemp
    0.47
    加油
    0.46
    *
    0.46
     Armin
    0.46
     Bezirk
    0.45
     Kopf
    0.45
    மணிய
    0.44
    Bel
    0.44
     Hofmann
    0.43
     বলিয়
    0.43
    Act Density 0.001%

    No Known Activations