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

    Neuronpedia

    INDEX
    Explanations

    Bachelor of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    त्रा
    0.43
    rusted
    0.40
     atmosphere
    0.39
     Lester
    0.39
    ඹ
    0.38
    ()),
    0.38
     माहौल
    0.38
    दों
    0.38
    ドラマ
    0.38
    Результа
    0.37
    POSITIVE LOGITS
     स्तरीय
    0.47
    '
    0.46
    ’
    0.46
    hood
    0.40
    stwa
    0.38
    ardom
    0.38
    PropertyChanged
    0.36
    ial
    0.36
     शेख
    0.35
     کنکریاں
    0.35
    Act Density 0.003%

    No Known Activations