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

    Neuronpedia

    INDEX
    Explanations

    ability to contribute positively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    近年来
    0.43
     argentino
    0.43
     alberga
    0.43
    buscar
    0.42
    _,
    0.41
     acessar
    0.41
     nazy
    0.41
    preneur
    0.41
    verde
    0.40
    vero
    0.40
    POSITIVE LOGITS
     satisfactorily
    0.57
     satisfactory
    0.57
     résultat
    0.48
     Résultats
    0.48
     result
    0.47
     résultats
    0.45
     problemlos
    0.43
     exact
    0.43
     परिणाम
    0.43
     results
    0.43
    Act Density 0.025%

    No Known Activations