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

    Neuronpedia

    INDEX
    Explanations

    Cannes, Nice, canned food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mannschaften
    0.80
     Расійскай
    0.75
     அனைவருக்கும்
    0.70
    ට්ට
    0.68
     Séb
    0.65
     Gern
    0.64
    fordul
    0.63
     Srivastava
    0.63
     इंग्लिश
    0.63
     ಅಭಿಮಾನ
    0.63
    POSITIVE LOGITS
    5
    0.93
    1
    0.92
     be
    0.72
    2
    0.72
    จะ
    0.67
    )$
    0.67
    <strong>
    0.63
    4
    0.63
    8
    0.62
    ),
    0.61
    Act Density 0.000%

    No Known Activations