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

    Neuronpedia

    INDEX
    Explanations

    origin or specific category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ellig
    0.43
    ika
    0.43
    nika
    0.40
    ৈত্র
    0.39
     entrambe
    0.39
     समुद्र
    0.39
     eil
    0.38
     getNodeId
    0.38
    nę
    0.38
     ristorante
    0.38
    POSITIVE LOGITS
     Errors
    0.49
     ignores
    0.47
     Ignore
    0.44
    errors
    0.42
     Fehler
    0.42
     errors
    0.42
    Errors
    0.42
    していない
    0.41
    اف
    0.41
    bleshooting
    0.40
    Act Density 0.006%

    No Known Activations